@theronap/agnoclast-mcp@0.9.262
Connect your AI assistant to Cortex — your org's projects, activity, gaps, and directives, scoped to you.
AI Security Review
scanned 12d ago · by lpm-firewall-aiSource inspection found no install-time execution or concrete attack behavior. The flagged configuration changes are associated with explicit setup or channel commands, and Antigravity wiring does not load its generated launch agent.
Decision evidence
public snapshot- package.json defines no install lifecycle hook; its scripts are release, promote, and rollback.
- The flagged agent configuration writes are reached through setup or channel commands and modify MCP or hook configuration.
- Codex setup requires a supplied token; Cursor preserves existing MCP entries and skips malformed configuration.
- Antigravity wiring writes files but does not load the launch agent.
- The inspected dependency manifests and entrypoints show ordinary SDK and validation-library exports.
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@0.9.262.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.262 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.