@theronap/agnoclast-mcp@0.9.193
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 package has no install lifecycle hook in its manifest, and the Antigravity integration is reached through an explicit install operation. Its LaunchAgent setup is a concrete first-party agent integration capability, but activation is left to the user, so a warning is appropriate rather than a block.
Decision evidence
public snapshot- package.json defines release, promote, and rollback scripts, with no npm lifecycle hook.
- The CLI calls setup only for the explicit setup command; the installer calls an adapter's wire method only for targeted editors.
- The Antigravity adapter writes a sync script and LaunchAgent plist, and tells the user to run launchctl load to activate the watcher.
- Codex, Cursor, and skills code describes configuration and skill setup; working_files reads Claude session files. These inspected paths do not establish a separate attack.
- capture.mjs resolves a token from the environment or wired machine configuration; the inspected excerpt alone does not show credential exfiltration.
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@0.9.193.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.193 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.