@theronap/agnoclast-mcp@0.9.291
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 lifecycle hooks, and the reviewed credential flow sends account proof to the configured Agnoclast service only for confidential-brain access. The flagged agent-configuration writes and launchd persistence are exposed through explicit CLI commands, with closeout documented as off by default.
Decision evidence
public snapshot- The manifest defines a CLI but no install, preinstall, or postinstall hook.
- Codex auth.json is read only when Codex is the nearest agent; its ID token is used as account proof for confidential-brain access.
- That proof is sent to the configured Agnoclast base only when a session requests a confidential brain.
- The closeout launchd job is off by default and is installed through the explicit closeout-install command.
- Channel configuration edits run only when a channel is explicitly selected.
Source & flagged code
17 flaggedSource file is highly similar to a previously finalized malicious package; route for source-aware review.
lib/capture.mjsView on unpkgPackage source references weak cryptographic algorithms.
lib/capture.mjsView on unpkg · L1Findings
Affected versions and remediation
This report applies to @theronap/agnoclast-mcp@0.9.291.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.291 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.