@theronap/agnoclast-mcp@0.9.230
Connect your AI assistant to Cortex — your org's projects, activity, gaps, and directives, scoped to you.
AI Security Review
scanned 20d ago · by lpm-firewall-aiSource inspection found no npm install hook or concrete attack behavior. The flagged configuration and watcher changes are part of explicit setup or cleanup commands, so the package is clean.
Decision evidence
public snapshot- package.json exposes a CLI and lists only release, promote, and rollback scripts; no npm lifecycle hook is declared.
- The CLI dispatches setup, install, and uninstall when those commands are invoked.
- Setup and editor adapters write Agnoclast configuration to assistant-specific locations; the Codex adapter skips wiring without a token.
- Skills are installed into Claude and Codex skill directories, uninstall removes managed entries, and transcript lookup uses a session ID under Claude project folders.
- Antigravity setup writes a watcher script and plist but does not load the watcher; it warns that the script depends on a local development checkout.
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@0.9.230.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.230 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.