@theronap/agnoclast-mcp@0.9.287
Connect your AI assistant to Cortex — your org's projects, activity, gaps, and directives, scoped to you.
AI Security Review
scanned 4d ago · by lpm-firewall-aiThe manifest has no install lifecycle hooks, and the flagged credential flow refuses API-key authentication rather than collecting or forwarding that key. The new scheduled closeout behavior requires an explicit CLI install command, so the reviewed findings do not show malicious default behavior.
Decision evidence
public snapshot- The manifest has no install, preinstall, or postinstall lifecycle scripts.
- The Anthropic key check refuses confidential-session identity proof when API-key or cloud-provider authentication is in use.
- The closeout sweep and LaunchAgent installer run only through explicit CLI subcommands.
- Closeout state is stored under the user's ~/.cortex/closeout directory.
- The opt-in closeout feature can periodically resume eligible Claude sessions and use the user's account.
- The CLI has a SessionStart path that can heal a confidential guard into Claude settings.
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@0.9.287.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.287 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.