@theronap/agnoclast-mcp@0.9.240
Connect your AI assistant to Cortex — your org's projects, activity, gaps, and directives, scoped to you.
AI Security Review
scanned 18d ago · by lpm-firewall-aiSource review found no npm install lifecycle hook, and the flagged agent configuration behavior is tied to explicit CLI commands. The Antigravity watcher is written but not activated by the installer, so no concrete attack surface was established.
Decision evidence
public snapshot- The manifest exposes a CLI and defines no npm install lifecycle hook; setup, install, capture, and uninstall run through explicit subcommands.
- Setup and install write the package’s MCP configuration and managed skills to detected editor locations; the reviewed adapters preserve or scope changes to those locations.
- Uninstall is an explicit command with dry-run and backup behavior; it removes managed MCP entries rather than adding agent configuration.
- The Antigravity adapter writes a watcher script and plist, but the plist is not loaded by the installer, has RunAtLoad disabled, and requires a separate load command to activate.
- The transcript helper searches the Claude projects directory for the requested session ID.
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@0.9.240.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.240 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.