@theronap/cortex-mcp@0.9.152
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 25d ago · by lpm-firewall-aiThe package has no npm install hook, but its explicit cross-editor installer can write a package-owned Antigravity watcher configuration. Since activation requires a separate manual step and no malicious chain was established, this warrants a capability warning rather than a block.
Decision evidence
public snapshot- The manifest defines release, promote, and rollback scripts; it has no install lifecycle hook.
- The explicit install command defaults to detected editors and calls each selected adapter's wire function.
- The Antigravity adapter writes a launch agent and sync script under the user's home directory.
- The launch agent watches Antigravity data, but RunAtLoad is disabled; the adapter does not load it automatically.
- Setup requires a token and writes the package's MCP configuration; skills are installed into Claude and Codex skill directories.
- Uninstall changes are behind the uninstall command and support a dry-run mode.
- No inspected source establishes covert execution, credential theft, or an unrelated network recipient.
- The Antigravity watcher requires separate manual activation, and its sync script points to a local development checkout.
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@0.9.152.
See all versions of @theronap/cortex-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/cortex-mcp@0.9.152 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.