@theronap/agnoclast-mcp@0.9.265
Connect your AI assistant to Cortex — your org's projects, activity, gaps, and directives, scoped to you.
AI Security Review
scanned 6d ago · by lpm-firewall-aiThe manifest has no install lifecycle hook, and the flagged configuration and persistence behaviors are reached through explicit setup, install or channel commands. Antigravity wiring leaves its launchd agent unloaded, so the scanner’s persistence and control-surface alerts do not establish an attack.
Decision evidence
public snapshot- package.json lists only release, promote and rollback scripts; it has no install lifecycle hook.
- The CLI reaches setup and install behavior only through explicit subcommands.
- Antigravity wiring writes a shell script and launchd plist but explicitly does not load the agent.
- Channel configuration changes run through the explicit `channel` command.
- The package’s stated purpose is to connect AI assistants to the organization’s Cortex service.
- The Antigravity watcher is inactive until a user loads it, and its generated script depends on a local development checkout.
- The inspected configuration writes support editor wiring and package-channel selection; no unrelated collector or hidden action 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@0.9.265.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.265 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.