ruflo-aidefence

1import type { Hook, Register } from 'claude-code'
2
3import { answer } from './command'
4import { owns, verdict } from './guard'
5import { readOptions } from './options'
6import { newStats, STATUS_PATH, statusText, type Stats } from './status'
7import type { ModOptions } from './options'
8
9type Dollar = Parameters<Hook<'session.start'>>[0]
10
11/** Everything one session of the mod keeps: its settings, counters and the project root. */
12type Session = { readonly opts: ModOptions; readonly stats: Stats; root?: string }
13
14async function flush($: Dollar, s: Session): Promise<void> {
15  if (s.root === undefined) return
16  try {
17    await $.fs.write(`${s.root}/${STATUS_PATH}`, statusText(s.stats, s.opts, await $.clock.now()))
18  } catch {
19    /* the status file is a courtesy */
20  }
21}
22
23/**
24 * AIDefence as a mod (ADR-445 pattern): a tighten-only guard on what `aidefence_learn` teaches the detector (patterns persist and are shown back later), `/aidefence-mod`, and a status file the console reads.
25 * No network, no process: only the hooks API.
26 */
27export const register: Register = (on, options) => {
28  const s: Session = { opts: readOptions(options), stats: newStats() }
29
30  on('session.start', async ($, e, next) => {
31    const result = await next(e)
32    s.root = (await $.session.root()) as string | undefined
33    s.stats.startedMs = await $.clock.now()
34    try {
35      await $.command.register({ name: 'aidefence-mod', description: 'AIDefence mod: status, scan <text>' })
36    } catch {
37      /* a name taken by another plugin must not stop the mod */
38    }
39    await flush($, s)
40    return result
41  })
42
43  if (s.opts.guard) {
44    on('tool.call', async ($, e, next) => {
45      if (!owns(e.tool, e)) return next(e)
46      s.stats.calls++
47      const reason = verdict(e.tool, e)
48      if (reason === undefined) return next(e)
49      s.stats.blocked++
50      await flush($, s)
51      return { deny: reason }
52    })
53  }
54
55  /** `/aidefence-mod` (a markdown command of the plugin cannot be answered by a hook, so the mod owns this name). */
56  on('command.run', { command: 'aidefence-mod' }, async (_$, e) => ({ text: answer(typeof e.args === 'string' ? e.args : '', { opts: s.opts, stats: s.stats }) }))
57}
58

1import { scan } from './screen'
2import type { ModOptions } from './options'
3import type { Stats } from './status'
4
5/** `/aidefence-mod` is answered locally and takes no model turn. */
6export type CommandDeps = { readonly opts: ModOptions; readonly stats: Stats }
7
8const HELP = ['/aidefence-mod status', '/aidefence-mod scan <text>'].join('\n')
9
10export function answer(args: string, deps: CommandDeps): string {
11  const [verb = '', ...rest] = args.trim().split(/\s+/)
12  const arg = rest.join(' ')
13  const { opts, stats } = deps
14
15  if (verb === '' || verb === 'help') return HELP
16
17  if (verb === 'status') {
18    return `guard ${opts.guard ? 'on' : 'off'} · calls guarded ${stats.calls} · blocked ${stats.blocked}`
19  }
20
21  if (verb === 'scan') {
22    if (arg === '') return 'usage: /aidefence-mod scan <text>'
23    const found = scan(arg)
24    const parts = [found.secrets.length ? `secrets: ${found.secrets.join(', ')}` : '', found.injection.length ? `injection phrasing: ${found.injection.join(', ')}` : ''].filter(Boolean)
25    return parts.length ? `The guard would refuse a write of that (${parts.join('; ')}).` : 'Nothing found: the guard would let that through.'
26  }
27
28  return `Unknown: ${verb}\n${HELP}`
29}
30

1import { hasSecret } from './screen'
2import { textsOf } from './screen'
3export { textsOf }
4
5/** `mcp__<server>__<tool>` into its two halves; tool names never hold a double underscore. */
6export function splitName(name: string): { server: string; tool: string } | undefined {
7  if (!name.startsWith('mcp__')) return undefined
8  const at = name.lastIndexOf('__')
9  return at > 5 ? { server: name.slice(5, at), tool: name.slice(at + 2) } : undefined
10}
11
12/** True for the tool calls this plugin guards: what `aidefence_learn` teaches the detector (patterns persist and are shown back later). */
13export function owns(tool: string, input: unknown): boolean {
14  const parts = splitName(tool)
15  const name = parts?.tool ?? tool
16  return name === 'aidefence_learn'
17}
18
19/** The reason a call is refused, or undefined when it may go. Never names or echoes the secret. */
20export function verdict(tool: string, input: unknown): string | undefined {
21  if (!owns(tool, input)) return undefined
22  return textsOf(input).some(hasSecret) ? "ruflo-aidefence: this learning sample holds what looks like a secret (a key, token or password). Learned patterns are stored and replayed; describe the shape of the threat, not the live value." : undefined
23}
24

1import type { PluginOptions } from 'claude-code'
2
3/** The plugin's `userConfig`, validated: a bad value is the default (guard on). */
4export type ModOptions = {
5  readonly guard: boolean
6}
7
8// BEGIN SHARED FLAG (generated by scripts/sync-mod-screen.mjs; edit plugins/ruflo-agentdb/hooks/options.ts)
9export const flag = (value: unknown, fallback: boolean) =>
10  value === true || value === 'true' || value === 'on' ? true : value === false || value === 'false' || value === 'off' ? false : fallback
11// END SHARED FLAG
12
13export function readOptions(options: PluginOptions | undefined): ModOptions {
14  const o = options ?? {}
15  return {
16    guard: flag(o.guard, true),
17  }
18}
19

1/** Counters the mod keeps for the session and writes to `.claude-flow/aidefence-mod/status.json` for the console. */
2export type Stats = { calls: number; blocked: number; startedMs: number }
3
4export const newStats = (): Stats => ({ calls: 0, blocked: 0, startedMs: 0 })
5
6export const STATUS_PATH = '.claude-flow/aidefence-mod/status.json'
7
8/** The file's text; `version` lets the console refuse a shape it does not know. */
9export function statusText(stats: Stats, mode: { guard: boolean }, nowMs: number): string {
10  return `${JSON.stringify({ version: 1, updatedMs: nowMs, mod: 'aidefence', guard: mode.guard, ...stats }, null, 2)}\n`
11}
12

1/**
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