@theronap/agnoclast-mcp@0.9.233
Connect your AI assistant to Cortex — your org's projects, activity, gaps, and directives, scoped to you.
AI Security Review
scanned 19d ago · by lpm-firewall-aiThe manifest has no npm lifecycle hooks, and the inspected configuration behavior is associated with explicit product setup or uninstall. The flagged Antigravity persistence is not activated by the adapter itself, so the source does not establish an attack.
Decision evidence
public snapshot- package.json lists only release, promote, and rollback scripts; no npm lifecycle hook is declared.
- Setup requires a user-supplied token and performs the assistant wiring through the explicit runSetup command.
- The Codex, Cursor, setup, skills, uninstall, and working-files locations describe editor configuration, managed skill paths, uninstall targets, or transcript lookup.
- The Antigravity adapter writes a script and launchd plist but does not load the watcher; its warning tells the user to activate it.
- The binary is an assistant connector with named subcommands, and the source shows no package-install trigger for the flagged configuration changes.
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/agnoclast-mcp@0.9.233.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.233 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.