@theronap/cortex-mcp@0.9.246
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 16d ago · by lpm-firewall-aiThe manifest has no install lifecycle hook, and the flagged configuration and persistence behavior is tied to explicit CLI commands. The inspected code provides no confirmed attack surface.
Decision evidence
public snapshot- package.json lists only release, promote, and rollback scripts; the CLI dispatches setup, install, and uninstall as explicit commands.
- Setup requires a supplied token and writes assistant configuration. The Codex and Cursor adapters check for a token before writing their respective configuration files.
- The skills installer writes skill files into Claude and Codex skill directories, backing up changed files.
- Uninstall runs only through its CLI command; its dry-run mode skips configuration writes.
- The transcript helper searches the local Claude projects directory for a file matching the supplied session ID.
- Antigravity setup writes a script and launchd plist but does not load the plist; its warning says a separate launchctl command is needed to activate the watcher.
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@0.9.246.
See all versions of @theronap/cortex-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/cortex-mcp@0.9.246 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.