@theronap/agnoclast-mcp@0.9.229
Connect your AI assistant to Cortex — your org's projects, activity, gaps, and directives, scoped to you.
AI Security Review
scanned 20d ago · by lpm-firewall-aiSource inspection found no npm install hook or confirmed malicious behavior. The flagged configuration and persistence changes are user-invoked product setup or removal, and the Antigravity agent is not loaded automatically.
Decision evidence
public snapshot- package.json defines a CLI and only release, promote, and rollback scripts; no npm install lifecycle hook is declared.
- The CLI routes setup, install, and uninstall through explicit subcommands. Setup backs up and merges editor configuration; install wires selected adapters.
- The reviewed editor locations describe bounded Codex and Cursor integrations, skills in user editor directories, uninstall cleanup, and local transcript lookup by session ID.
- Antigravity setup writes a script and launch-agent file, but the generated agent has RunAtLoad disabled and setup instructs the user to load it manually.
- The runtime requires a Cortex token obtained from the Agnoclast console and sends session requests through the configured Cortex API base; no unrelated recipient or hidden credential transfer 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@0.9.229.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.229 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.