@clear-capabilities/agentic-security-scanner 0.132.0 → 0.133.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +125 -0
- package/bin/agentic-security.js +20 -1
- package/dist/113.index.js +3 -3
- package/dist/178.index.js +1 -1
- package/dist/384.index.js +1 -1
- package/dist/526.index.js +3 -3
- package/dist/637.index.js +1 -1
- package/dist/agentic-security.mjs +22 -22
- package/dist/agentic-security.mjs.sha256 +1 -1
- package/package.json +4 -3
- package/src/engine.js +32 -1
- package/src/llm-validator/cost-ceiling.js +199 -0
- package/src/llm-validator/index.js +241 -12
- package/src/llm-validator/local-endpoint.js +90 -0
- package/src/posture/accuracy-scorecard.js +37 -6
- package/src/posture/corpus-match.js +29 -14
- package/src/posture/integrity.js +42 -9
- package/src/posture/learning.js +8 -1
- package/src/posture/model-routing.js +26 -0
- package/src/posture/model-trust.js +174 -0
- package/src/posture/poc-inprocess.js +165 -0
- package/src/posture/prove-findings.js +148 -0
- package/src/posture/rule-overrides.js +64 -3
- package/src/posture/state-dir.js +25 -0
- package/src/posture/vuln-archaeology.js +231 -0
- package/src/report/index.js +7 -0
- package/src/sandbox/CLAUDE.md +27 -5
- package/src/sandbox/backend-namespace.js +39 -11
- package/src/sandbox/backend-userspace.js +4 -0
- package/src/sast/CLAUDE.md +4 -0
- package/src/sast/crypto-specialist.js +247 -0
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,130 @@
|
|
|
1
1
|
# Changelog
|
|
2
2
|
|
|
3
|
+
## 0.133.0 — two ways findings could be silently deleted, both closed
|
|
4
|
+
|
|
5
|
+
Four rounds of adversarial premortem against this repository's own artifacts.
|
|
6
|
+
Two rounds found working exploits in shipped code; both are fixed and both are
|
|
7
|
+
pinned by tests that run the original attack. The rest is measurement honesty —
|
|
8
|
+
several gates turned out to prove less than they claimed, including one defect
|
|
9
|
+
this effort introduced and then caught.
|
|
10
|
+
|
|
11
|
+
### Security
|
|
12
|
+
|
|
13
|
+
- **A signature anyone could forge could disable any detector.**
|
|
14
|
+
`verifyLastScan` accepted a second key derived as
|
|
15
|
+
`sha256(<constant salt> + ':' + hostname)`. The salt is a constant in
|
|
16
|
+
published, npm-shipped source and a hostname is not a secret. Because the
|
|
17
|
+
`disable:` list in `rules.yml` is gated on that verification, a signature
|
|
18
|
+
forged from public information alone switched off arbitrary detectors and the
|
|
19
|
+
scan reported clean. Demonstrated end to end: a command-injection finding went
|
|
20
|
+
from 1 reported to 0, and back to 1 after the fix.
|
|
21
|
+
|
|
22
|
+
This had been known and fixed once already. The 0.62.0 entry below introduced
|
|
23
|
+
the per-install key precisely because the old one was "hostname-derived and
|
|
24
|
+
publicly forgeable in CI / containers", and kept legacy verification "for one
|
|
25
|
+
release to migrate existing signed scans". It was still accepted **seventy
|
|
26
|
+
minor releases later**. A migration window nobody closes is not a migration
|
|
27
|
+
window; it is the vulnerability, kept. Verification now accepts exactly one
|
|
28
|
+
key. Signatures made under the legacy key stop verifying — intended, and it
|
|
29
|
+
fails closed.
|
|
30
|
+
|
|
31
|
+
- **The LLM validator cache was a finding-deletion primitive.** A cache hit
|
|
32
|
+
assigned a verdict directly, and a `reject` verdict drops a finding. The cache
|
|
33
|
+
was read with a bare `JSON.parse(readFileSync(...))`, so planting one file
|
|
34
|
+
under `.agentic-security/llm-cache/` deleted a critical finding with no model
|
|
35
|
+
call and no network. The key is derivable by anyone with repo access, and CI
|
|
36
|
+
restoring a cache directory between runs delivers it without a repo write at
|
|
37
|
+
all. Cache entries are now HMAC-signed with the same mechanism `last-scan.json`
|
|
38
|
+
already used; an unsigned, tampered or foreign-keyed entry is a MISS, never a
|
|
39
|
+
verdict.
|
|
40
|
+
|
|
41
|
+
- **A `reject` can no longer delete a strongly-provenanced finding.** The code
|
|
42
|
+
asserted that prompt-injecting the validator was harmless because "the worst
|
|
43
|
+
an attacker can produce is escalate". That was false: the challenge/nonce
|
|
44
|
+
cross-check defends against forged and replayed responses, not against a model
|
|
45
|
+
persuaded by source it legitimately read. Findings from real analysis
|
|
46
|
+
(taint-proven, multi-sink, execution-proven) are now demoted to `escalate`
|
|
47
|
+
rather than dropped, so the guarantee is structural instead of asserted.
|
|
48
|
+
|
|
49
|
+
- **Coverage reduction is now visible in the artifact.** A `disable:` that took
|
|
50
|
+
effect produced findings that were simply absent — indistinguishable from
|
|
51
|
+
clean code to whoever reads the report. `suppressedRules` now carries the
|
|
52
|
+
count, per-rule severity breakdown, example locations and the AUTHORITY the
|
|
53
|
+
suppression ran under, so a signed suppression reads differently from an
|
|
54
|
+
env-var opt-out. Authorised suppressions are reported too: a signature proves
|
|
55
|
+
who asked, not that the hidden findings stopped existing.
|
|
56
|
+
|
|
57
|
+
- **Signatures carry key provenance** (`env` / `per-install` / `ephemeral`).
|
|
58
|
+
`env` means whoever set the environment could have signed the run; `ephemeral`
|
|
59
|
+
means the key could not be persisted and the signature will never verify
|
|
60
|
+
again. Neither was inferable from the digest.
|
|
61
|
+
|
|
62
|
+
- **The suppression quorum has a floor of 2.** `AGENTIC_SECURITY_LEARN_QUORUM=1`
|
|
63
|
+
was honoured, so a single triage verdict could suppress a finding — and with
|
|
64
|
+
family+path matching, a whole family across a path. The root guidance warned
|
|
65
|
+
about exactly this; the code did not enforce it.
|
|
66
|
+
|
|
67
|
+
### Measurement honesty
|
|
68
|
+
|
|
69
|
+
- **The corpus is fitted to the detectors it measures, and now says so.** 98% of
|
|
70
|
+
entries are self-authored synthetic fixtures and none come from the
|
|
71
|
+
disclosed-PoC tier. `npm run corpus:provenance` prints the composition on every
|
|
72
|
+
run and fails a commit that lands a detector together with the corpus entries
|
|
73
|
+
exercising it — caught against real history, including one such commit in this
|
|
74
|
+
very effort. This stops the loop tightening; it does not make the corpus
|
|
75
|
+
independent, and the docs no longer imply otherwise.
|
|
76
|
+
|
|
77
|
+
- **The precision gate covered 6% of the source.** It ran over `hooks/` and
|
|
78
|
+
`scripts/` — 22 files — while `scanner/src` (383 files, the entire product) sat
|
|
79
|
+
outside it. Now 240 files. The `scanner/src` count is published as a DRIFT
|
|
80
|
+
TRIPWIRE, explicitly not hand-reviewed and explicitly not a precision figure,
|
|
81
|
+
because a scanner's own source contains sink patterns as data.
|
|
82
|
+
|
|
83
|
+
- **The determinism gate exercised only the layer that cannot vary.** The
|
|
84
|
+
original fixture produced findings from regex and structural detectors alone. A
|
|
85
|
+
second fixture now drives the interprocedural taint engine and the Python
|
|
86
|
+
parser, digests are compared per fixture so a divergence names the layer, and
|
|
87
|
+
the comparator fails if the deep fixture degraded to the syntactic layer on any
|
|
88
|
+
machine.
|
|
89
|
+
|
|
90
|
+
- **The scorecard gate could not detect a stale scorecard.** It compared only the
|
|
91
|
+
engine version, so a document measured over 200 corpus entries passed while the
|
|
92
|
+
corpus held 210 — every published rate computed over a population that no
|
|
93
|
+
longer existed. It now compares the population too.
|
|
94
|
+
|
|
95
|
+
- **The independent-evaluation gate passed on a 4-sample smoke fixture** its own
|
|
96
|
+
README says must never be cited, because its thresholds had been calibrated to
|
|
97
|
+
pass. It now uses the README's own figures, treats exceeded calibration targets
|
|
98
|
+
as violations rather than notes, and refuses to emit a pass over the built-in
|
|
99
|
+
fixture however the thresholds are set. It fails today, correctly.
|
|
100
|
+
|
|
101
|
+
- **Claims re-scoped to what is measured.** The roadmap carries a "What the gates
|
|
102
|
+
do not prove" section, states outright that the false-positive-rate goal is not
|
|
103
|
+
met, and points at the two harnesses built for that gap — both of which need
|
|
104
|
+
data, not code. R13 is downgraded from "landed" to "mechanism landed, no
|
|
105
|
+
observation pipeline": nothing constructs its ledger, so it can never downgrade
|
|
106
|
+
anything.
|
|
107
|
+
|
|
108
|
+
### Fixed along the way
|
|
109
|
+
|
|
110
|
+
- **The validator cache had never persisted a single entry.** `safeWriteState`
|
|
111
|
+
refused every directory nested under `.agentic-security/`, so `llm-cache/`,
|
|
112
|
+
`fix-history/` and `sbom-history/` were all unwritable while a
|
|
113
|
+
`validator-cache stats|gc` subcommand managed a cache that was always empty.
|
|
114
|
+
Found by a positive-control test asserting a legitimately written entry
|
|
115
|
+
round-trips.
|
|
116
|
+
|
|
117
|
+
- **Sandbox timeouts now use SIGKILL.** The kernel does not deliver
|
|
118
|
+
default-action signals to a PID namespace's pid 1 from outside it, so SIGTERM
|
|
119
|
+
was dropped and a payload ran to completion against a 1200 ms budget — measured
|
|
120
|
+
in CI at 30057 ms. Proof execution also gained its own aggregate wall-clock
|
|
121
|
+
budget, because a count cap bounds nothing in time.
|
|
122
|
+
|
|
123
|
+
- **Cost reporting stopped presenting an estimate as spend.** The endpoint's
|
|
124
|
+
usage report was discarded, so the ledger always booked the pre-call worst
|
|
125
|
+
case. Usage is now plumbed through, and any estimated component renders as
|
|
126
|
+
"at most $X" with the reason.
|
|
127
|
+
|
|
3
128
|
## 0.132.0 — a proven exploit becomes a permanent regression test
|
|
4
129
|
|
|
5
130
|
The corpus stops being only a regression net and starts being fed by the engine
|
package/bin/agentic-security.js
CHANGED
|
@@ -17,7 +17,7 @@ import { recordScan, formatStreakLine, formatGradeDelta } from '../src/posture/s
|
|
|
17
17
|
import { ingestAndMerge } from '../src/sca/sarif-ingest.js';
|
|
18
18
|
import { loadProfile, saveProfile, detectProfile, renderAttributionLine, ATTRIBUTION, ATTRIBUTION_URL } from '../src/posture/profile.js';
|
|
19
19
|
import { applySuppressions, addSoftAcceptance, expiredSoftAcceptances } from '../src/posture/suppressions.js';
|
|
20
|
-
import { applyOverrides, validateOverrides } from '../src/posture/rule-overrides.js';
|
|
20
|
+
import { applyOverrides, validateOverrides, suppressionReport, renderSuppressionSummary } from '../src/posture/rule-overrides.js';
|
|
21
21
|
import { listPacks, loadPack, applyPacks } from '../src/posture/rule-packs.js';
|
|
22
22
|
import { writeLockfile, verifyLockfile, makeDeterministic, isDeterministic } from '../src/posture/deterministic.js';
|
|
23
23
|
import { enrichWithEPSS } from '../src/posture/epss.js';
|
|
@@ -512,6 +512,19 @@ async function cmdScan(args) {
|
|
|
512
512
|
scan.findings = applyOverrides(scan.findings || [], targetAbs);
|
|
513
513
|
scan.secrets = applyOverrides(scan.secrets || [], targetAbs);
|
|
514
514
|
scan.logicVulns = applyOverrides(scan.logicVulns || [], targetAbs);
|
|
515
|
+
// Coverage reduction belongs in the ARTIFACT, not only in a log line. A
|
|
516
|
+
// `disable:` that takes effect otherwise produces findings that are simply
|
|
517
|
+
// absent, which is indistinguishable from clean code to whoever reads the
|
|
518
|
+
// report. Recorded whether the suppression was authorised or not — an
|
|
519
|
+
// authorised one still hides results.
|
|
520
|
+
try {
|
|
521
|
+
const _sup = suppressionReport(targetAbs);
|
|
522
|
+
if (_sup) {
|
|
523
|
+
scan.suppressedRules = _sup;
|
|
524
|
+
const _line = renderSuppressionSummary(_sup);
|
|
525
|
+
if (_line) process.stderr.write(`⚠️ agentic-security: ${_line}\n`);
|
|
526
|
+
}
|
|
527
|
+
} catch { /* reporting must never fail a scan */ }
|
|
515
528
|
|
|
516
529
|
// Curated rule packs: --pack <name> (repeatable). Narrows findings to the
|
|
517
530
|
// CWEs covered by the requested pack(s).
|
|
@@ -575,6 +588,7 @@ async function cmdScan(args) {
|
|
|
575
588
|
// only — a failure here must never fail a scan.
|
|
576
589
|
try {
|
|
577
590
|
const { computeRunAttestation } = await import('../src/posture/attestation.js');
|
|
591
|
+
const { keyProvenance } = await import('../src/posture/integrity.js');
|
|
578
592
|
const { effectiveVersion } = await import('../src/posture/ruleset-version.js');
|
|
579
593
|
scan.attestation = computeRunAttestation({
|
|
580
594
|
findings: normalizeFindings(scan),
|
|
@@ -584,6 +598,11 @@ async function cmdScan(args) {
|
|
|
584
598
|
root: targetAbs,
|
|
585
599
|
sign: true,
|
|
586
600
|
});
|
|
601
|
+
// P1-3 — a signature is only as meaningful as the key behind it.
|
|
602
|
+
// `env` means whoever set the environment could have signed this;
|
|
603
|
+
// `ephemeral` means the key could not be persisted, so this signature will
|
|
604
|
+
// never verify on any later run. Neither is inferable from the digest.
|
|
605
|
+
if (scan.attestation) scan.attestation.keyProvenance = keyProvenance();
|
|
587
606
|
} catch { /* attestation is metadata; never fail a scan over it */ }
|
|
588
607
|
|
|
589
608
|
// R2: Always emit machine-readable artifacts to .agentic-security/.
|
package/dist/113.index.js
CHANGED
|
@@ -406,8 +406,8 @@ var external_node_child_process_ = __webpack_require__(1421);
|
|
|
406
406
|
var external_node_fs_ = __webpack_require__(3024);
|
|
407
407
|
// EXTERNAL MODULE: external "node:path"
|
|
408
408
|
var external_node_path_ = __webpack_require__(6760);
|
|
409
|
-
// EXTERNAL MODULE: ./src/engine.js +
|
|
410
|
-
var engine = __webpack_require__(
|
|
409
|
+
// EXTERNAL MODULE: ./src/engine.js + 600 modules
|
|
410
|
+
var engine = __webpack_require__(5865);
|
|
411
411
|
;// CONCATENATED MODULE: ./src/posture/fix-honesty-gate.js
|
|
412
412
|
// Deterministic honesty gates on fix / finding output (#7).
|
|
413
413
|
//
|
|
@@ -946,7 +946,7 @@ async function verifyFix({
|
|
|
946
946
|
let pocLeg = { status: 'not-requested', reason: null, tier: null };
|
|
947
947
|
if (poc?.code) {
|
|
948
948
|
try {
|
|
949
|
-
const { proveFinding } = await
|
|
949
|
+
const { proveFinding } = await Promise.resolve(/* import() */).then(__webpack_require__.bind(__webpack_require__, 1291));
|
|
950
950
|
const proved = await proveFinding({ ...(poc.finding || {}), poc }, { files });
|
|
951
951
|
const tier = proved.proofTier;
|
|
952
952
|
pocLeg = tier === 'execution-proven'
|
package/dist/178.index.js
CHANGED
|
@@ -13,7 +13,7 @@ export const modules = {
|
|
|
13
13
|
/* harmony import */ var node_child_process__WEBPACK_IMPORTED_MODULE_0__ = __webpack_require__(1421);
|
|
14
14
|
/* harmony import */ var node_fs__WEBPACK_IMPORTED_MODULE_1__ = __webpack_require__(3024);
|
|
15
15
|
/* harmony import */ var node_path__WEBPACK_IMPORTED_MODULE_2__ = __webpack_require__(6760);
|
|
16
|
-
/* harmony import */ var _engine_js__WEBPACK_IMPORTED_MODULE_3__ = __webpack_require__(
|
|
16
|
+
/* harmony import */ var _engine_js__WEBPACK_IMPORTED_MODULE_3__ = __webpack_require__(5865);
|
|
17
17
|
// Time-travel + counterfactual scanning (v0.68).
|
|
18
18
|
//
|
|
19
19
|
// Two new modes that exploit the pure-input shape of runFullScan:
|
package/dist/384.index.js
CHANGED
|
@@ -8,7 +8,7 @@ export const modules = {
|
|
|
8
8
|
/* harmony export */ __webpack_require__.d(__webpack_exports__, {
|
|
9
9
|
/* harmony export */ scanCredentials: () => (/* reexport safe */ _engine_js__WEBPACK_IMPORTED_MODULE_0__.Sv)
|
|
10
10
|
/* harmony export */ });
|
|
11
|
-
/* harmony import */ var _engine_js__WEBPACK_IMPORTED_MODULE_0__ = __webpack_require__(
|
|
11
|
+
/* harmony import */ var _engine_js__WEBPACK_IMPORTED_MODULE_0__ = __webpack_require__(5865);
|
|
12
12
|
// Secrets submodule view of the engine — credential + entropy + TODO scanning.
|
|
13
13
|
|
|
14
14
|
|
package/dist/526.index.js
CHANGED
|
@@ -234,8 +234,8 @@ var external_node_child_process_ = __webpack_require__(1421);
|
|
|
234
234
|
var external_node_fs_ = __webpack_require__(3024);
|
|
235
235
|
// EXTERNAL MODULE: external "node:path"
|
|
236
236
|
var external_node_path_ = __webpack_require__(6760);
|
|
237
|
-
// EXTERNAL MODULE: ./src/engine.js +
|
|
238
|
-
var engine = __webpack_require__(
|
|
237
|
+
// EXTERNAL MODULE: ./src/engine.js + 600 modules
|
|
238
|
+
var engine = __webpack_require__(5865);
|
|
239
239
|
;// CONCATENATED MODULE: ./src/posture/fix-honesty-gate.js
|
|
240
240
|
// Deterministic honesty gates on fix / finding output (#7).
|
|
241
241
|
//
|
|
@@ -774,7 +774,7 @@ async function verifyFix({
|
|
|
774
774
|
let pocLeg = { status: 'not-requested', reason: null, tier: null };
|
|
775
775
|
if (poc?.code) {
|
|
776
776
|
try {
|
|
777
|
-
const { proveFinding } = await
|
|
777
|
+
const { proveFinding } = await Promise.resolve(/* import() */).then(__webpack_require__.bind(__webpack_require__, 1291));
|
|
778
778
|
const proved = await proveFinding({ ...(poc.finding || {}), poc }, { files });
|
|
779
779
|
const tier = proved.proofTier;
|
|
780
780
|
pocLeg = tier === 'execution-proven'
|
package/dist/637.index.js
CHANGED
|
@@ -11,7 +11,7 @@ export const modules = {
|
|
|
11
11
|
/* harmony export */ renderPrDeltaText: () => (/* binding */ renderPrDeltaText)
|
|
12
12
|
/* harmony export */ });
|
|
13
13
|
/* harmony import */ var node_child_process__WEBPACK_IMPORTED_MODULE_0__ = __webpack_require__(1421);
|
|
14
|
-
/* harmony import */ var _engine_js__WEBPACK_IMPORTED_MODULE_1__ = __webpack_require__(
|
|
14
|
+
/* harmony import */ var _engine_js__WEBPACK_IMPORTED_MODULE_1__ = __webpack_require__(5865);
|
|
15
15
|
// Shadowscan / security-DELTA on PR (v0.72).
|
|
16
16
|
//
|
|
17
17
|
// Most SAST PR-comment integrations show absolute counts — "12 findings
|