@theronap/agnoclast-mcp@0.9.228
Connect your AI assistant to Cortex — your org's projects, activity, gaps, and directives, scoped to you.
AI Security Review
scanned 25d ago · by lpm-firewall-aiThe manifest has no install lifecycle hooks, and the inspected configuration paths are consistent with an explicitly invoked Cortex assistant integration. The scanner hints do not establish malicious behavior.
Decision evidence
public snapshot- package.json declares no install lifecycle hooks and lists only release, promote, and rollback scripts.
- The CLI exposes setup as a user-invoked command; setup code describes wiring the assistant configuration.
- Codex and Cursor integrations are editor-specific; Codex’s cited section documents supported hooks, and Cursor’s describes capture behavior.
- Skills target managed assistant skill directories, while uninstall code identifies the package’s own configuration paths.
- Antigravity’s cited adapter describes a sync integration; the CLI is the declared executable entrypoint.
- Capture code imports its queue and Cortex client components for session capture.
Source & flagged code
6 flaggedThis package version adds a dangerous source file absent from the previous stored version; 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@0.9.228.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.228 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.