@theronap/agnoclast-mcp@0.9.246
Connect your AI assistant to Cortex — your org's projects, activity, gaps, and directives, scoped to you.
AI Security Review
scanned 16d ago · by lpm-firewall-aiThe manifest has no install lifecycle hook, and the inspected configuration changes are initiated through explicit CLI commands. The flagged Antigravity persistence is not automatically activated: setup does not load the agent and its plist disables RunAtLoad.
Decision evidence
public snapshot- package.json defines no install lifecycle hooks; its scripts are release, promote, and rollback commands.
- Setup requires a supplied token and writes the assistant configuration as part of the explicit setup flow.
- The Codex, Cursor, skills, uninstall, and transcript helpers target their named local configuration or project paths; no attack behavior is established by the inspected locations.
- Uninstall is an explicit command, and its changes are limited to removing Agnoclast-managed entries.
- Antigravity setup writes a watcher file and launch agent but does not load it; the generated plist has RunAtLoad disabled.
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@0.9.246.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.246 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.