@theronap/agnoclast-mcp@0.9.167
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-time execution or concrete attack behavior. The flagged agent configuration and persistence behavior is part of user-invoked Agnoclast setup, and Antigravity activation is left to the user.
Decision evidence
public snapshot- package.json defines no preinstall, install, or postinstall hook; its scripts are release, promote, and rollback.
- The command-line entrypoint presents setup as an explicit command that wires assistant configuration.
- Codex and Cursor adapters detect their respective user configuration directories and describe their capture behavior.
- Setup wires Codex only when its configuration directory exists; bundled skills target Claude Code and Codex.
- Uninstall edits named Agnoclast configuration and removes managed skills, with a dry-run option.
- Antigravity writes launchd artifacts but does not load them; activation requires a separate user action.
- Token resolution reads the configured environment or wired assistant configuration; no unrelated credential recipient was identified.
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@0.9.167.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.167 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.