@theronap/cortex-mcp@0.9.278
Renamed to @theronap/agnoclast-mcp — use that. Existing installs switch themselves to the new name on next start.
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 package’s flagged credential flow sends proof to the configured Cortex service; `https://api.openai.com/auth` is parsed as a JWT claim namespace, not contacted. Persistence-related artifacts require an explicit install command and the launchd job is not loaded automatically.
Decision evidence
public snapshot- The manifest exposes a CLI and lists only release, promote, and rollback scripts; it declares no install lifecycle hook.
- The confidential-session proof is sent to the configured Cortex API endpoint, and the OpenAI URL string is used to parse a JWT claim locally, not as a network destination.
- The Antigravity watcher artifacts are written only through the explicit install path; the adapter does not load the launchd job and tells the user to activate it manually.
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/cortex-mcp@0.9.278.
See all versions of @theronap/cortex-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/cortex-mcp@0.9.278 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.