@theronap/agnoclast-mcp@0.9.234
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-aiThe manifest has no install lifecycle hooks, and inspected agent configuration changes are tied to explicit CLI commands and scoped to this product. The flagged persistence behavior does not activate automatically because the generated launch agent is not loaded and has RunAtLoad disabled.
Decision evidence
public snapshot- package.json defines a CLI entrypoint and has no preinstall, install, or postinstall hook.
- The dispatcher runs setup and uninstall only when those commands are invoked.
- The Codex and Cursor adapters detect their respective user configuration directories; Cursor wiring merges this package's MCP entry while preserving other servers.
- Skills are installed into Claude and Codex skill directories; uninstall is an explicit command that removes Agnoclast wiring.
- Antigravity wiring writes a script and launch agent, but does not load the agent; its plist has RunAtLoad disabled.
- The working-files helper locates a transcript by session ID and reads it; no attack behavior is established by this code.
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@0.9.234.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.234 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.