@theronap/agnoclast-mcp@0.9.257
Connect your AI assistant to Cortex — your org's projects, activity, gaps, and directives, scoped to you.
AI Security Review
scanned 13d ago · by lpm-firewall-aiThe manifest has no npm install lifecycle hook, and the flagged agent configuration and persistence behavior is reached through explicit setup. The Antigravity watcher requires separate manual activation, so the inspected source does not establish an attack surface.
Decision evidence
public snapshot- package.json lists a CLI entry point and release scripts, with no npm install lifecycle hook.
- The setup and editor writes are reached through the explicit setup command; the inspected adapters write MCP configuration and a capture hook.
- Antigravity setup writes a watcher definition but instructs the user to activate it manually; its script depends on a local checkout.
- The inspected dependency manifests contain no install scripts, and the inspected Zod entry points re-export the library.
- Uninstall filters for Cortex or Agnoclast namespaced launch agents and removes those artifacts.
- The package can write AI editor configuration and a launch agent during explicit setup; these are persistent integration capabilities, but the inspected source does not show an unconsented install-time trigger.
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@0.9.257.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.257 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.