registry / @theronap/agnoclast-mcp / 0.9.295
@theronap/agnoclast-mcp@0.9.295
Connect your AI assistant to Cortex — your org's projects, activity, gaps, and directives, scoped to you.
AI Security Review
scanned 2d ago · by lpm-firewall-aiThe reviewed credential flow sends account proof to the configured Agnoclast API as part of opening a confidential brain. There are no install hooks, and the background scheduler requires an explicit command; the flagged configuration self-heal adds only the package's own guard hook.
Static reason
No blocking static signals were detected.; source matched previously finalized malicious package; routed for review
Trigger
Confidential account proof is sent when a confidential brain is opened; the close-out scheduler is installed only when its CLI command is run. A SessionStart status hook can self-heal the package's guard hook.
Impact
No malicious behavior found in the inspected paths.
Mechanism
The confidential flow posts proof to the configured Agnoclast API with the user's Agnoclast token. The scheduler writes and loads a launchd job only on explicit installation. The self-heal adds only the package's guard hook to Claude settings.
AI rationale
The reviewed credential flow sends account proof to the configured Agnoclast API as part of opening a confidential brain. There are no install hooks, and the background scheduler requires an explicit command; the flagged configuration self-heal adds only the package's own guard hook.
Evidence
~/.claude/settings.json~/Library/LaunchAgents/com.agnoclast.closeout.plist
Network endpoints1
${base}/api/brains/confidential/agent-session
Decision evidence
public snapshotAI called this Clean at 94.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The manifest exposes a CLI and declares no install lifecycle hooks.
- Confidential account proof is sent to the configured Agnoclast base URL with the user's Agnoclast token.
- The server requests account proof when opening a confidential brain; the flow is tied to that tool action.
- Background close-out is off by default and is installed through an explicit CLI command.
- Session startup may add the package's confidential guard hook to Claude settings; it adds only that hook.
Evidence against
- The package reads Codex or Claude account identity for confidential-brain access, but the inspected flow sends proof to the Agnoclast service using the user's Agnoclast token.
- The package can create a launchd job, but only through the explicit closeout-install command.
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetwork
HighEntropyStringsUrlStrings
Source & flagged code
17 flaggedlib/capture.mjsView file
•matchType = normalized_sha256
matchedPackage = @theronap/agnoclast-mcp@0.9.293
matchedPath = lib/capture.mjs
matchedIdentity = npm:QHRoZXJvbmFwL2Fnbm9jbGFzdC1tY3A:0.9.293
similarity = 1.000
summary = normalized source hash matched finalized malicious source
High
Known Malware Source Similarity
Source file is highly similar to a previously finalized malicious package; route for source-aware review.
lib/capture.mjsView on unpkg1import { readFileSync, accessSync, constants, openSync, mkdirSync } from 'fs'
L2: import { spawn, execFileSync } from 'child_process'
L3: import { homedir } from 'os'
...
L21: if (!res.ok) return null
L22: const j = await res.json().catch(() => ({}))
L23: return Array.isArray(j.types) ? j.types : null
...
L35: try {
L36: if (resolve(String(cwd)) === homedir()) return 'general'
L37: } catch { /* unresolvable path — fall through to basename */ }
...
L45: //
L46: // Handles the four remote forms git emits: scp-like ssh (git@github.com:o/n.git), ssh://, https://,
L47: // git://. The HOST CHECK IS LOAD-BEARING, not cosmetic: this string becomes a clearance key, and
Low
Weak Crypto
Package source references weak cryptographic algorithms.
lib/capture.mjsView on unpkg · L1lib/editors/antigravity.mjs
Findings
15 High3 Medium5 Low
HighTrigger Reachable External Ai Agent Control Surface Mutationlib/channel.mjs
HighTrigger Reachable Persistencelib/closeout.mjs
HighSemantic Analysis Limitedbin/cortex-mcp.mjs#virtual:normalized:round1
HighKnown Malware Source Similaritylib/confidential_session.mjs
HighKnown Malware Source Similaritylib/login.mjs
HighKnown Malware Source Similaritylib/closeout.mjs
HighKnown Malware Source Similaritylib/capture.mjs
HighKnown Malware Source Similaritylib/edge_extract.mjs
HighKnown Malware Source Similaritylib/graphify_sync.mjs
HighKnown Malware Source Similaritylib/obligations_worker.mjs
HighKnown Malware Source Similarity
Affected versions and remediation
This report applies to @theronap/agnoclast-mcp@0.9.295.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.295 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.