Knowledge graph construction — entity extraction, relation mapping, and pathfinder graph traversal. As a mod (ADR-445): keeps secrets out of the graph…

Knowledge graph construction -- entity extraction, relation mapping, and pathfinder graph traversal.
Extracts entities (classes, functions, modules, types, concepts) and relations (imports, extends, implements, depends-on, calls) from source code and documentation. Builds a navigable knowledge graph stored in AgentDB with hierarchical nodes and causal edges. Traverses the graph using a pathfinder algorithm that scores paths by edge weight and semantic similarity.
claude --plugin-dir plugins/ruflo-knowledge-graph
| Agent | Model | Role |
|---|---|---|
graph-navigator | sonnet | Entity extraction, relation mapping, knowledge graph construction, pathfinder traversal |
| Skill | Usage | Description |
|---|---|---|
kg-extract | /kg-extract <path> | Extract entities and relations from source files to build a knowledge graph |
kg-traverse | /kg-traverse <entity> [--depth N] | Pathfinder traversal starting from a seed entity |
kg extract <path> # Extract entities and relations from source files
kg traverse <entity> # Pathfinder traversal from a seed entity
kg relations <entity> # List all direct relations for an entity
kg visualize # ASCII visualization of the knowledge graph
kg search <query> # Semantic search across the graph
| Type | Examples |
|---|---|
| class | UserService, AuthController |
| function | calculateDiscount, handleRequest |
| module | auth, payments, api |
| concept | authentication, caching |
| type | User, OrderStatus |
| config | database, redis, jwt |
@claude-flow/cli v3.6 major+minor.bash plugins/ruflo-knowledge-graph/scripts/smoke.sh is the contract.This plugin owns the knowledge-graph AgentDB namespace (kebab-case, follows the convention from ruflo-agentdb ADR-0001 §"Namespace convention"). Reserved namespaces (pattern, claude-memories, default) MUST NOT be shadowed.
Entity nodes are stored via agentdb_hierarchical-store; relation edges via agentdb_causal-edge; semantic indexing via embeddings_generate (NOT embeddings_embed — that tool name doesn't exist; ADR-0001 fixes prior references).
relevance = edge_weight * semantic_similarity(query, node)ADR-095 closed five AgentDB controllers that this plugin's graph traversal can leverage:
gnnService — GNN embeddings + relational scoring over the AgentDB causal graph. Augments the pathfinder's semantic_similarity(query, node) term with structurally-aware scoring; nodes that are graph-neighbors of confirmed-relevant nodes get a boost.rvfOptimizer — Quantizes + dedupes vector blocks before persistence. Knowledge-graph indexes commonly have many near-duplicate entity vectors (same class re-exported from multiple modules); rvfOptimizer collapses them transparently.mutationGuard + attestationLog + GuardedVectorBackend — Proof-gated writes to the underlying vector store. Relevant when the graph spans trust boundaries (federated knowledge import) — the attestation chain at .swarm/attestation.db records every mutation for after-the-fact audit.The yet-pending graphAdapter controller will give this plugin a first-class graph-DB backend (instead of building the graph view on top of AgentDB's flat causal-edge table). Tracked in ADR-095.
Inspect runtime status via the agentdb_controllers or agentdb_health MCP tools.
bash plugins/ruflo-knowledge-graph/scripts/smoke.sh
# Expected: "10 passed, 0 failed"
ruflo-agentdb -- The G7 controllers above ship via this plugin's runtime; install both for full graph + traversal coverage; namespace convention ownerruflo-ruvector -- HNSW indexing for fast semantic search across graph nodesruflo-adr -- ADR dependency graphs share the same causal edge modelMIT
This plugin ships a function-hook mod (ADR-445, hooks/register.ts). It makes no network call, spawns no process and makes no model call.
agentdb_causal-edge, agentdb_hierarchical-store, agentdb_pattern-store) that hold a key, token or password, and agentdb_causal-edge-delete / agentdb_causal-node-delete unless the call carries confirm: true. A refusal never echoes the secret./kg-mod: status, recent, tools (which of this plugin's tools are connected) and scan <text> (would the guard refuse it). Answered locally..claude-flow/kg-mod/status.json ({version: 1, updatedMs, guard, calls, total, blocked, recent}, counters only, never tool input), written at session start and after every call to this plugin's tools.Options (userConfig): guard (on), confirmDeletes (on).
Test it: claude plugin validate plugins/ruflo-knowledge-graph, claude plugin test plugins/ruflo-knowledge-graph, bash plugins/ruflo-knowledge-graph/scripts/smoke.sh.
hooks/register.ts 109 lines1import type { Hook, Register } from 'claude-code'
2
3import { isOwn, shortName, verdict } from './guard'
4import { readOptions, type ModOptions } from './options'
5import { scan } from './screen'
6
7const COMMAND = 'kg-mod'
8const STATUS_PATH = '.claude-flow/kg-mod/status.json'
9const RECENT = 5
10
11type Dollar = Parameters<Hook<'session.start'>>[0]
12
13/** Everything one session of the mod keeps: its settings, per-tool counters, what was refused and the project root. */
14type Session = {
15 readonly opts: ModOptions
16 readonly calls: Record<string, number>
17 blocked: number
18 readonly recent: string[]
19 root?: string
20}
21
22const total = (s: Session) => Object.values(s.calls).reduce((a, b) => a + b, 0)
23
24function note(s: Session, line: string): void {
25 s.recent.push(line)
26 if (s.recent.length > RECENT) s.recent.splice(0, s.recent.length - RECENT)
27}
28
29/** The status file the console reads; `version` lets it refuse a shape it does not know. Counters only, never tool input. */
30async function flush($: Dollar, s: Session): Promise<void> {
31 if (s.root === undefined) return
32 const body = { version: 1, updatedMs: await $.clock.now(), guard: s.opts.guard, ...s.opts.extra, calls: s.calls, total: total(s), blocked: s.blocked, recent: s.recent }
33 try {
34 await $.fs.write(`${s.root}/${STATUS_PATH}`, `${JSON.stringify(body, null, 2)}\n`)
35 } catch {
36 /* the status file is a courtesy */
37 }
38}
39
40/** The connected tools this plugin owns, by short name. */
41async function connected($: Dollar): Promise<string[]> {
42 const tools = await $.tool.list()
43 return tools.filter(t => t.mcp && isOwn(shortName(t.name))).map(t => shortName(t.name))
44}
45
46const HELP = ['/kg-mod status', '/kg-mod scan <text>', '/kg-mod recent', '/kg-mod tools'].join('\n')
47
48async function answer($: Dollar, s: Session, args: string): Promise<string> {
49 const [verb = '', ...rest] = args.trim().split(/\s+/)
50 const arg = rest.join(' ')
51 if (verb === '' || verb === 'help') return HELP
52 if (verb === 'status') {
53 const per = Object.entries(s.calls).map(([k, v]) => `${k} ${v}`).join(' · ')
54 return [`guard ${s.opts.guard ? 'on' : 'off'}${Object.entries(s.opts.extra).map(([k, v]) => ` · ${k} ${String(v)}`).join('')}`, `${total(s)} call${total(s) === 1 ? '' : 's'}${per ? ` (${per})` : ''} · refused ${s.blocked}`].join('\n')
55 }
56 if (verb === 'recent') return s.recent.length ? s.recent.map(r => `- ${r}`).join('\n') : 'Nothing has gone through this session.'
57 if (verb === 'tools') {
58 const names = await connected($)
59 return names.length ? names.join('\n') : 'None of this plugin\'s tools are connected. Connect the ruflo MCP server and try again.'
60 }
61 if (verb === 'scan') {
62 if (arg === '') return 'usage: /kg-mod scan <text>'
63 const found = scan(arg)
64 return found.secrets.length ? `The guard would refuse that (${found.secrets.join(', ')}).` : 'Nothing found: the guard would let that through.'
65 }
66 return `Unknown: ${verb}\n${HELP}`
67}
68
69/**
70 * Knowledge graph as a mod (ADR-445): a tighten-only guard on this plugin's own tools, a status file the console reads, and `/kg-mod`.
71 * No network, no process, no model call.
72 */
73export const register: Register = (on, options) => {
74 const s: Session = { opts: readOptions(options), calls: {}, blocked: 0, recent: [] }
75
76 on('session.start', async ($, e, next) => {
77 const result = await next(e)
78 s.root = (await $.session.root()) as string | undefined
79 try {
80 await $.command.register({ name: COMMAND, description: 'Knowledge graph mod: status, scan <text>, recent, tools' })
81 } catch {
82 /* a name taken by another plugin must not stop the mod */
83 }
84 await flush($, s)
85 return result
86 })
87
88 on('tool.call', async ($, e, next) => {
89 const name = shortName(e.tool)
90 if (!isOwn(name, e)) return next(e)
91 if (s.opts.guard) {
92 const reason = verdict(name, e, s.opts, s.calls)
93 if (reason !== undefined) {
94 s.blocked++
95 note(s, `refused ${name}`)
96 await flush($, s)
97 return { deny: reason }
98 }
99 }
100 s.calls[name] = (s.calls[name] ?? 0) + 1
101 note(s, name)
102 await flush($, s)
103 return next(e)
104 })
105
106 /** `/kg-mod`: the plugin's own commands are prompt commands, which no hook can answer. */
107 on('command.run', { command: COMMAND }, async ($, e) => ({ text: await answer($, s, typeof e.args === 'string' ? e.args : '') }))
108}
109hooks/guard.ts 43 lines1import { hasSecret } from './screen'
2import type { ModOptions } from './options'
3import { textsOf } from './screen'
4export { textsOf }
5
6/** `mcp__<server>__<tool>` into its tool half; tool names never hold a double underscore. */
7export function shortName(name: string): string {
8 const at = name.lastIndexOf('__')
9 return name.startsWith('mcp__') && at > 5 ? name.slice(at + 2) : name
10}
11
12const field = (input: unknown, key: string): unknown => (typeof input === 'object' && input !== null ? (input as Record<string, unknown>)[key] : undefined)
13
14
15const OWN = new Set([
16 'agentdb_causal-edge',
17 'agentdb_causal-edge-delete',
18 'agentdb_causal-node-delete',
19 'agentdb_hierarchical-store',
20 'agentdb_hierarchical-recall',
21 'agentdb_pattern-store',
22 'agentdb_pattern-search',
23 'agentdb_context-synthesize',
24 'agentdb_semantic-route',
25 'embeddings_generate',
26])
27const WRITERS = new Set(['agentdb_causal-edge', 'agentdb_hierarchical-store', 'agentdb_pattern-store'])
28const DELETERS = new Set(['agentdb_causal-edge-delete', 'agentdb_causal-node-delete'])
29
30/** The tools this plugin owns: the AgentDB graph and pattern tools its skills name. */
31export const isOwn = (name: string, _input?: unknown): boolean => OWN.has(name)
32
33/** The reason a call is refused, or undefined when it may go. Never names or echoes a secret. */
34export function verdict(name: string, input: unknown, opts: ModOptions, _calls: Record<string, number>): string | undefined {
35 if (WRITERS.has(name) && textsOf(input).some(hasSecret)) {
36 return 'ruflo-knowledge-graph: this graph write holds what looks like a secret (a key, token or password). Store a reference to where it lives, not the value.'
37 }
38 if (opts.confirmDeletes && DELETERS.has(name) && field(input, 'confirm') !== true) {
39 return 'ruflo-knowledge-graph: deleting graph nodes or edges cannot be undone. Ask the user, then retry with confirm: true.'
40 }
41 return undefined
42}
43hooks/options.ts 16 lines1import type { PluginOptions } from 'claude-code'
2
3/** The plugin's `userConfig`, validated: a bad value is the default (guard on, graph deletes confirmed). */
4export type ModOptions = { readonly guard: boolean; readonly confirmDeletes: boolean; readonly extra: Readonly<Record<string, unknown>> }
5
6// BEGIN SHARED FLAG (generated by scripts/sync-mod-screen.mjs; edit plugins/ruflo-agentdb/hooks/options.ts)
7export const flag = (value: unknown, fallback: boolean) =>
8 value === true || value === 'true' || value === 'on' ? true : value === false || value === 'false' || value === 'off' ? false : fallback
9// END SHARED FLAG
10
11export function readOptions(options: PluginOptions | undefined): ModOptions {
12 const o = options ?? {}
13 const confirmDeletes = flag(o.confirmDeletes, true)
14 return { guard: flag(o.guard, true), confirmDeletes, extra: { confirmDeletes } }
15}
16hooks/screen.ts 261 lines1/**
2 * Pure text screening for the AgentDB mod (ADR-445). Two jobs: find secrets (so none is stored) and find prompt-injection phrasing (so
3 * retrieved memory cannot instruct the model). Findings are NAMES only: the matched text is never returned, logged or counted by value.
4 */
5
6// BEGIN SHARED SCREEN (generated from plugins/ruflo-agentdb/hooks/screen.ts by scripts/sync-mod-screen.mjs; do not edit in a copy)
7export type Rules = readonly (readonly [string, RegExp])[]
8
9/** The secret shapes every mod screens for. A plugin adds its own after these, outside the markers. */
10export const COMMON_SECRETS: Rules = [
11 ['private key', /-----BEGIN [A-Z ]*PRIVATE KEY-----/],
12 ['aws access key', /\b(?:AKIA|ASIA)[0-9A-Z]{16}\b/],
13 ['github token', /\b(?:gh[pousr]_[A-Za-z0-9]{30,}|github_pat_[A-Za-z0-9_]{40,})\b/],
14 ['slack token', /\bxox[abprs]-[A-Za-z0-9-]{10,}/],
15 ['slack webhook', /\bhooks\.slack\.com\/services\/T[A-Z0-9]{6,}\/B[A-Z0-9]{6,}\/[A-Za-z0-9]{16,}/],
16 ['google api key', /\bAIza[0-9A-Za-z_-]{35}\b/],
17 ['anthropic or openai key', /\bsk-(?:(?:ant|proj|svcacct|admin)-[A-Za-z0-9_-]{20,}|(?=[A-Za-z]{0,40}\d)[A-Za-z0-9]{32,})/],
18 ['stripe key', /\b[rs]k_live_[A-Za-z0-9]{16,}/],
19 ['npm token', /\bnpm_[A-Za-z0-9]{36}\b/],
20 ['huggingface token', /\bhf_[A-Za-z0-9]{30,}\b/],
21 ['sendgrid key', /\bSG\.[A-Za-z0-9_-]{16,}\.[A-Za-z0-9_-]{16,}/],
22 ['twilio key', /\bSK[0-9a-f]{32}\b/],
23 ['jwt', /\beyJ[A-Za-z0-9_-]{8,}\.eyJ[A-Za-z0-9_-]{8,}\.[A-Za-z0-9_-]{8,}/],
24 ['bearer token', /\bBearer\s+([A-Za-z0-9._~+/=-]{24,})/],
25 ['database url with credentials', /\b[a-z][a-z0-9+.-]{1,20}:\/\/[^\s:@/]+:[^\s@/]{3,}@[^\s/]+/i],
26]
27
28export const INJECTION: Rules = [
29 ['override instructions', /\b(?:ignore|disregard|forget|override)\b[^.\n]{0,40}\b(?:previous|prior|above|earlier|all|any|system)\b[^.\n]{0,30}\b(?:instructions?|rules?|prompts?|guidelines?)\b/i],
30 ['role reassignment', /\byou are (?:now|no longer)\b|\bact as (?:an? )?(?:unrestricted|jailbroken)\b/i],
31 ['new instructions', /\b(?:new|updated|real) (?:system )?instructions?\s*:/i],
32 ['fake role tags', /<\/?\s*(?:system|assistant|developer|instructions?)\s*>|^\s*(?:system|assistant)\s*:/im],
33 ['concealment', /\bdo not (?:tell|inform|mention|reveal)[^.\n]{0,30}\b(?:user|human|operator)\b/i],
34 ['exfiltration', /\b(?:exfiltrate|send|post|upload)\b[^.\n]{0,50}\b(?:secrets?|credentials?|tokens?|api keys?|\.env)\b/i],
35 ['shell pipe', /\b(?:curl|wget)\b[^|\n]{0,200}\|\s*(?:sudo\s+)?(?:ba|z)?sh\b/i],
36]
37
38// C0/C1 controls (keeping tab and newline), DEL, soft hyphen, combining grapheme joiner, Arabic letter mark, Hangul and Mongolian fillers/separators,
39// zero-width, bidi (overrides and isolates) and invisible-format characters, variation selectors; built with escapes, never raw.
40const INVISIBLE = new RegExp(
41 '[\\u0000-\\u0008\\u000b-\\u001f\\u007f-\\u009f\\u00ad\\u034f\\u061c\\u115f\\u1160\\u17b4\\u17b5\\u180b-\\u180e\\u200b-\\u200f\\u2028-\\u202e\\u2060-\\u206f\\u3164\\ufe00-\\ufe0f\\ufeff\\uffa0\\ufff9-\\ufffb]',
42 'g',
43)
44
45/** Longest input scanned in one pass; a longer one keeps its head and tail halves. One regex pass per rule, so cost stays linear. */
46const MAX_SCAN = 200_000
47
48/** Input bounded to MAX_SCAN characters with invisible characters removed, so none can hide a secret or a phrase. */
49export const bare = (text: string) =>
50 (text.length > MAX_SCAN ? text.slice(0, MAX_SCAN / 2) + '\n' + text.slice(-MAX_SCAN / 2) : text).replace(INVISIBLE, '')
51
52// A value is a secret CANDIDATE only when it is not a reference (env var, call, identifier path, placeholder, secret-manager path) and its
53// shape is random enough: at least two character classes, one of them a digit or symbol, and Shannon entropy of at least 2.5 bits per character.
54const PLACEHOLDER = /placeholder|your[-_ ]|example|changeme|change[-_]?me|redacted|dummy|replace[-_]?me|insert[-_]|\*{3,}|x{5,}|\.{3}|^(?:none|null|undefined|true|false)$/i
55const REFERENCE =
56 /^(?:\$(?:\{[^}]*\}|\(|[A-Za-z_]\w*$)|%[^%]*%$|<[^>]*>$|\{\{|process\.env|os\.environ|env[.[]|import\.meta|System\.getenv|secrets?\.|vault:|op:\/\/|ref\+|arn:|projects\/[^/]+\/secrets\/|gcp:|kms:|aws:|file:)/i
57const CALL = /^[A-Za-z_$][\w$]*(?:\.[A-Za-z_$][\w$]*)*\(|^[A-Za-z_$][\w$]*\[/
58const IDENT_PATH = /^[A-Za-z_$][\w$]*(?:\.[A-Za-z_$][\w$]*)+$/
59const UUID = /^[0-9a-f]{8}-(?:[0-9a-f]{4}-){3}[0-9a-f]{12}$/i
60const NAME_LIKE = /^[a-z][a-z0-9]*(?:[-_./][a-z0-9]+){2,}$/
61
62function entropy(v: string): number {
63 const counts = new Map<string, number>()
64 for (const ch of v) counts.set(ch, (counts.get(ch) ?? 0) + 1)
65 let h = 0
66 for (const n of counts.values()) h -= (n / v.length) * Math.log2(n / v.length)
67 return h
68}
69
70/** True when `v` is a name, call, path or placeholder rather than a literal credential. */
71function isReference(v: string): boolean {
72 if (PLACEHOLDER.test(v) || REFERENCE.test(v) || CALL.test(v) || IDENT_PATH.test(v) || URL_NO_CREDS.test(v)) return true
73 return NAME_LIKE.test(v) && v.replace(/\D/g, '').length / v.length < 0.15
74}
75
76export function plausibleSecret(v: string): boolean {
77 if (v.length < 8 || v.length > 256 || /\s/.test(v) || UUID.test(v) || isReference(v)) return false
78 const symbol = /[^A-Za-z0-9]/.test(v)
79 const digit = /\d/.test(v)
80 const classes = [/[a-z]/.test(v), /[A-Z]/.test(v), digit, symbol].filter(Boolean).length
81 return classes >= 2 && (digit || symbol) && entropy(v) >= 2.5
82}
83
84/** Under a secret-named key a literal this long is a secret even with one character class or a UUID shape, unless it is a clear reference. */
85const KEYED_MIN = 20
86const PLACEHOLDER_WORD = /(?:^|[^a-z])(?:your|placeholder|changeme|change[-_]?me|example|redacted|dummy|replace[-_]?me|insert)(?:[^a-z]|$)|\*{3,}|x{5,}|\.{3}|^(?:none|null|undefined|true|false)$/i
87const URL_NO_CREDS = /^[a-z][a-z0-9+.-]{1,20}:\/\/[^\s@]*$/i
88
89/** Three or more lowercase hyphen-separated words (no hex or digit-only run of 8+, few digits), such as my-k8s-secret-name-for-database. */
90function hyphenName(v: string): boolean {
91 const parts = v.split('-')
92 return parts.length >= 3 && parts.every(p => /^[a-z0-9]{2,}$/.test(p) && !/^[0-9a-f]{8,}$/.test(p)) && v.replace(/\D/g, '').length / v.length < 0.15
93}
94
95function keyedSecret(v: string): boolean {
96 if (v.length < KEYED_MIN || v.length > 256 || /\s/.test(v)) return false
97 return !(PLACEHOLDER_WORD.test(v) || REFERENCE.test(v) || CALL.test(v) || IDENT_PATH.test(v) || URL_NO_CREDS.test(v) || (!UUID.test(v) && hyphenName(v)))
98}
99
100const KEY_NAME = /(?:api[_-]?key|secret|token|passw(?:or)?d|passwd|pwd|credential|private[_-]?key|auth(?!or))s?[A-Za-z0-9_-]{0,40}["']?\s*[:=]\s*/gi
101const QUOTED = /(["'\x60])((?:(?!\1)[^\n]){1,256})\1/y
102const BARE_VALUE = /[^\s"'\x60,;]{1,256}/y
103const QUERY_VALUE = /[^\s"'\x60,;&]{1,256}/y
104
105/** A secret-named key assigned a literal value: env style, JSON, YAML, code. Values that are calls, references or placeholders do not count. */
106function assignmentSecret(text: string): boolean {
107 let valueEnd = 0
108 for (const m of text.matchAll(KEY_NAME)) {
109 if (m.index < valueEnd) continue // a key-looking word inside the previous value, such as secretsmanager in an ARN
110 const at = m.index + m[0].length
111 let back = m.index
112 while (back > 0 && m.index - back < 64 && /[A-Za-z0-9_.-]/.test(text.charAt(back - 1))) back--
113 const re = /["'\x60]/.test(text.charAt(at)) ? QUOTED : /[?&]/.test(text.charAt(back - 1)) ? QUERY_VALUE : BARE_VALUE
114 re.lastIndex = at
115 const hit = re.exec(text)
116 const v = hit && (hit[2] ?? hit[0])
117 valueEnd = hit ? at + hit[0].length : at
118 if (v && (plausibleSecret(v) || keyedSecret(v))) return true
119 }
120 return false
121}
122
123/** A password in a URL's userinfo that is not a placeholder such as user:password or ${DB_PASSWORD}. */
124function urlCredential(url: string): boolean {
125 const pass = /^[^:]+:\/\/[^\s:@/]+:([^\s@/]+)@/.exec(url)?.[1]
126 if (!pass || /\$\{|\{\{|%\(|%s/.test(pass)) return false
127 return !/^(?:password|passwd|pass|pwd|secret|changeme|dbpassword|db_password|\$\w*|<.*>|\{.*\}|\*+|x+)$/i.test(pass) && !PLACEHOLDER.test(pass)
128}
129
130const CHECKS: Readonly<Record<string, (m: RegExpMatchArray) => boolean>> = {
131 'bearer token': m => !isReference(m[1] ?? ''),
132 'database url with credentials': m => urlCredential(m[0]),
133 'database url with password': m => urlCredential(m[0]),
134}
135const globals = new WeakMap<RegExp, RegExp>()
136
137function matches(name: string, re: RegExp, text: string): boolean {
138 if (name === 'key assignment') return assignmentSecret(text)
139 const check = CHECKS[name]
140 if (!check) return re.test(text)
141 let g = globals.get(re)
142 if (!g) globals.set(re, (g = new RegExp(re.source, re.flags.includes('g') ? re.flags : re.flags + 'g')))
143 for (const m of text.matchAll(g)) if (check(m)) return true
144 return false
145}
146
147/**
148 * The text textsOf appends when it had to drop input (a node, character or per-string budget ran out). It is never matched against a rule:
149 * `names` reports it as a finding of its own, so every guard that asks "is there a secret in these texts" refuses what it could not read in full.
150 */
151export const TRUNCATED = 'ruflo-screen: input exceeded the screening budget'
152export const TRUNCATED_NAME = 'input too large to screen'
153
154/** Names of the rules that match `text` (already bare'd). A rule named 'key assignment' is judged by assignmentSecret, whatever its regex. */
155export const names = (rules: Rules, text: string) => text === TRUNCATED ? [TRUNCATED_NAME] : rules.filter(([name, re]) => matches(name, re, text)).map(([name]) => name)
156
157export type Findings = { readonly secrets: readonly string[]; readonly injection: readonly string[] }
158
159/** Names of every secret shape in `secrets` and every injection phrase found in `text`. Cost is linear in the capped input. */
160export function screenWith(secrets: Rules, text: string): Findings {
161 const bounded = bare(text)
162 return { secrets: names(secrets, bounded), injection: names(INJECTION, bounded) }
163}
164
165export const hasSecretIn = (secrets: Rules, text: string) => names(secrets, bare(text)).length > 0
166
167/** Makes stored text safe to show: no control or bidi characters, whitespace collapsed, at most `max` characters. */
168export function tidy(text: string, max: number): string {
169 const flat = text.replace(INVISIBLE, '').replace(/\s+/g, ' ').trim()
170 return flat.length > max ? `${flat.slice(0, Math.max(0, max - 1))}…` : flat
171}
172/** Bounds for textsOf: nodes visited, characters returned, the longest string read in full, the size of one returned chunk, chunk overlap. */
173export type TextLimits = { readonly nodes?: number; readonly chars?: number; readonly perString?: number }
174const NODES = 20_000
175const CHARS = 2_000_000
176const PER_STRING = 1_500_000
177const OVERLAP = 2_048
178const BARE_KEY_MIN = 8
179
180/** A string as texts the screen can read whole: one text up to MAX_SCAN, else overlapping MAX_SCAN windows so a secret anywhere is inside one. */
181function windows(text: string, out: string[]): void {
182 if (text.length <= MAX_SCAN) {
183 out.push(text)
184 return
185 }
186 for (let at = 0; ; at += MAX_SCAN - OVERLAP) {
187 out.push(text.slice(at, at + MAX_SCAN))
188 if (at + MAX_SCAN >= text.length) return
189 }
190}
191
192/**
193 * Every string in a tool input, for the screen to read: iterative (no recursion, so nesting 5000 deep cannot overflow the stack) and
194 * breadth-first (siblings before depth, so a long list cannot hide a nested value). A string under an object key comes back as `key=value`,
195 * so a secret-named key is judged with its value; a key whose value is not a string is returned bare. Strings longer than the screen window
196 * come back as overlapping windows; one over `perString` keeps its head and tail. Work is bounded by `nodes` slots and `chars` characters.
197 * Anything dropped (slots or characters ran out, or a string lost its middle) is reported by a final TRUNCATED text, which `names` and
198 * `hasSecretIn` count as a finding, so the screen fails closed instead of passing what it did not read.
199 */
200export function textsOf(input: unknown, limits: TextLimits = {}): string[] {
201 const out: string[] = []
202 let slots = limits.nodes ?? NODES
203 let chars = limits.chars ?? CHARS
204 const perString = limits.perString ?? PER_STRING
205 let truncated = false
206 const take = (text: string): void => {
207 if (chars <= 0) {
208 truncated = true
209 return
210 }
211 if (text.length <= Math.min(perString, chars)) {
212 chars -= text.length
213 windows(text, out)
214 return
215 }
216 truncated = true
217 const half = Math.floor(Math.min(perString, chars) / 2)
218 chars -= 2 * half
219 windows(text.slice(0, half), out)
220 windows(text.slice(-half), out)
221 }
222 const queue: unknown[] = [input]
223 let head = 0
224 for (; head < queue.length && chars > 0; head++) {
225 const node = queue[head]
226 if (typeof node === 'string') take(node)
227 else if (Array.isArray(node)) {
228 let i = 0
229 for (; i < node.length && slots > 0; i++, slots--) if (i in node) queue.push(node[i])
230 if (i < node.length) truncated = true
231 } else if (typeof node === 'object' && node !== null) {
232 for (const k in node) {
233 if (slots-- <= 0) {
234 truncated = true
235 break
236 }
237 if (!Object.prototype.hasOwnProperty.call(node, k)) continue
238 const v = (node as Record<string, unknown>)[k]
239 if (typeof v === 'string') queue.push(k + '=' + v)
240 else {
241 if (k.length >= BARE_KEY_MIN) take(k)
242 queue.push(v)
243 }
244 }
245 }
246 }
247 if (queue.length > head) truncated = true
248 if (truncated) out.push(TRUNCATED)
249 return out
250}
251// END SHARED SCREEN
252
253const SECRETS: Rules = [
254 ...COMMON_SECRETS,
255 ['key assignment', /\b(?:api[_-]?key|secret|token|passw(?:or)?d|credential)s?["']?\s*[:=]\s*["']?[A-Za-z0-9/+=_.-]{16,}/i],
256]
257
258export const scan = (text: string): Findings => screenWith(SECRETS, text)
259
260export const hasSecret = (text: string) => hasSecretIn(SECRETS, text)
261