@theronap/agnoclast-mcp@0.9.158
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-aiThe source supports a warning for agent skill installation and synchronization, but does not establish malicious behavior. The package has no npm lifecycle hook, and the relevant writes are part of its CLI setup and skill-sync flow.
Decision evidence
public snapshot- lib/setup.mjs calls the managed-skill installer and syncs organization-published skills during setup.
- lib/skills.mjs fetches skills from the configured Agnoclast service using the wired token, then installs them into detected agent CLI skill directories.
- The synced content can add or update behavior-bearing instructions in an AI agent’s skill surface; source does not establish a separate user approval for each update.
- package.json defines no preinstall, install, or postinstall hook; configuration changes require running the CLI setup or install flow.
- The Codex and Cursor adapters merge only the package’s own MCP entries while preserving other servers.
- The Antigravity adapter writes a watcher configuration but does not load it; activation requires a separate launchctl command.
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@0.9.158.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.158 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.