@theronap/cortex-mcp@0.9.276
Renamed to @theronap/agnoclast-mcp — use that. Existing installs switch themselves to the new name on next start.
Connect your AI assistant to Cortex — your org's projects, activity, gaps, and directives, scoped to you.
AI Security Review
scanned 6d ago · by lpm-firewall-aiThe server automatically reads a Codex identity token and sends it to agnoclast.com during startup when a confidential seat is found. This is credential disclosure to the package service without a startup consent prompt, so the package is malicious.
Decision evidence
public snapshot- On MCP server startup, if the initial seat lookup finds confidential brains, the server gathers agent proof and sends it in a second lookup.
- For Codex, gathering proof reads the id_token from ~/.codex/auth.json.
- The confidential-brain lookup sends the proof in a POST request body.
- The package’s default service host is agnoclast.com.
- The proof lookup is tied to the package’s confidential-brain account feature, and is conditional on the first lookup finding a seat.
- Antigravity’s launch agent is only generated by its explicit install wiring; the package says it does not load the agent automatically.
Source & flagged code
6 flaggedPackage source references weak cryptographic algorithms.
lib/capture.mjsView on unpkg · L1Findings
Affected versions and remediation
This report applies to @theronap/cortex-mcp@0.9.276.
See all versions of @theronap/cortex-mcp for other recorded verdicts.
- Avoid installing @theronap/cortex-mcp@0.9.276. Remove it from direct dependencies and check your lockfile for transitive copies.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
- If this version ran, investigate the affected machine and build environment. Rotate credentials it could access and rebuild from a trusted environment.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.