registry / @theronap/agnoclast-mcp / 0.9.298
@theronap/agnoclast-mcp@0.9.298
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 manifest has no install hook, and the flagged persistence behavior is off by default and requires an explicit install command. The inspected confidential-session code refuses Claude API credentials and sends identity proof to the configured Agnoclast service for its session feature.
Static reason
No blocking static signals were detected.; source matched previously finalized malicious package; routed for review
Trigger
Running the relevant CLI subcommands; closeout persistence requires `closeout-install`.
Impact
No unauthorized credential transfer or automatic persistence was established in the reviewed paths.
Mechanism
Channel changes edit existing Agnoclast entries in agent configuration. Closeout can install a launchd job that processes eligible Claude Code sessions and records digests through the package service.
AI rationale
The manifest has no install hook, and the flagged persistence behavior is off by default and requires an explicit install command. The inspected confidential-session code refuses Claude API credentials and sends identity proof to the configured Agnoclast service for its session feature.
Evidence
~/.claude.json~/.claude/settings.json~/.codex/hooks.json~/.codex/config.toml~/.cursor/mcp.json~/Library/LaunchAgents/com.agnoclast.closeout.plist
Network endpoints1
agnoclast.com
Decision evidence
public snapshotAI called this Clean at 91.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The manifest has no install lifecycle hook; its scripts are release, promote, and rollback commands.
- The launcher reaches closeout installation only through the explicit `closeout-install` subcommand.
- The closeout launch agent is documented as off by default and is installed by that explicit command.
- Confidential-session proof is used in requests to the configured Agnoclast service; Claude API keys and auth tokens cause the account proof to be refused.
Evidence against
- The scanner flags configuration writes and persistence, but the inspected channel command performs writes only when explicitly given a channel, and the launch agent requires explicit installation.
- The scanner flags an Anthropic credential flow to api.openai.com; the inspected code refuses Claude API credentials and sends Codex identity proof to the configured Agnoclast endpoint.
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetwork
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@0.9.298.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.298 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.