@theronap/agnoclast-mcp@0.9.224
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-aiSource inspection found no npm lifecycle trigger or concrete attack behavior. The scanner's persistence and configuration findings correspond to explicit product setup paths, and the Antigravity watcher requires manual activation.
Decision evidence
public snapshot- package.json exposes a CLI and declares release, promote, and rollback scripts; it declares no npm install lifecycle hook.
- Setup, install, and uninstall are named CLI commands. The CLI describes setup as wiring the MCP server and capture hook, and uninstall supports a no-write dry run.
- The reviewed agent integration paths use editor detection, explicit setup hooks, managed skill locations, and local transcript lookup.
- Antigravity setup writes a sync script and launch agent, but the plist disables launch-at-load and the installer requires a separate manual activation command.
- Runtime requests use the configured service token with an API base that defaults to agnoclast.com; custom CORTEX_URL values are operator-configured.
- The SHA-1 use in capture derives a short local working-directory key for a cache lookup.
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@0.9.224.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.224 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.