registry / @theronap/agnoclast-mcp / 0.9.303
@theronap/agnoclast-mcp@0.9.303
Connect your AI assistant to Cortex — your org's projects, activity, gaps, and directives, scoped to you.
AI Security Review
scanned 1d ago · by lpm-firewall-aiThe manifest has no install lifecycle hook, and the reviewed credential path uses AI account proof for confidential-brain access through the package’s service. The flagged background job and configuration edits are reached through explicit commands; the OpenAI URL is only a locally parsed JWT claim namespace.
Static reason
No blocking static signals were detected.; source matched previously finalized malicious package; routed for review
Trigger
The CLI server starts when invoked; closeout persistence and channel changes require their respective explicit CLI commands.
Impact
No unauthorized credential transfer, install-time action, or unrequested persistence was identified.
Mechanism
The reviewed account proof is used for confidential-brain access through the Agnoclast API. The OpenAI URL appears as a local JWT claim key, not as a contacted endpoint.
AI rationale
The manifest has no install lifecycle hook, and the reviewed credential path uses AI account proof for confidential-brain access through the package’s service. The flagged background job and configuration edits are reached through explicit commands; the OpenAI URL is only a locally parsed JWT claim namespace.
Evidence
$HOME/Library/LaunchAgents/com.agnoclast.closeout.plist$HOME/.claude.json$HOME/.claude/settings.json$HOME/.codex/hooks.json$HOME/.cursor/mcp.json$HOME/.codex/config.toml
Decision evidence
public snapshotAI called this Clean at 92.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The manifest has no install, preinstall, or postinstall lifecycle hook; it exposes an explicit CLI entrypoint.
- The server gathers an AI account proof only when confidential-brain seats exist, and confidential access is requested through the Agnoclast API.
- The OpenAI URL string is used as a JWT claim namespace while parsing a token locally; the inspected code does not send the token to OpenAI.
- The closeout launch agent is described as off by default and is installed through a dedicated CLI subcommand.
- Channel configuration changes run only when the user supplies a channel to the channel command.
Evidence against
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@0.9.303.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.303 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.