@theronap/agnoclast-mcp@0.9.153
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-aiSource inspection found no npm install lifecycle hook, and the agent configuration changes are reached through explicit setup or uninstall actions. Antigravity wiring leaves activation to the user, so the flagged persistence does not establish an attack surface.
Decision evidence
public snapshot- package.json declares no preinstall, install, or postinstall hook; its scripts are release, promote, and rollback.
- The setup routine takes a token argument and writes assistant configuration when explicitly invoked.
- Codex and Cursor adapters detect their respective user configuration directories before wiring.
- Antigravity wiring writes a sync script and launch agent file but explicitly does not load the agent; activation requires a separate user command.
- Uninstall changes agent configuration only when run, with a dry-run option.
- The explicit setup path adds assistant hooks and skills, while Antigravity wiring creates a launch agent file; these are persistent agent integrations but are user-invoked and not automatically activated at install.
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@0.9.153.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.153 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.