@theronap/cortex-mcp@0.9.162
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 inspected files show an explicitly invoked assistant integration and package-owned setup or cleanup behavior, with no npm install lifecycle hook or concrete malicious behavior established. The flagged persistence and agent configuration behavior is consistent with the package’s setup and uninstall functions.
Decision evidence
public snapshot- package.json exposes a CLI and lists only release, promote, and rollback scripts; no install lifecycle hook is declared.
- Codex and Cursor configuration is wired through editor adapters that detect whether those editors are present.
- Setup presents itself as an onboarding action; the CLI dispatches uninstall to a separate command.
- Antigravity integration creates a launchd sync agent, but it is part of explicit setup rather than an npm install hook.
- The shared token resolver is used by setup and capture; no evidence inspected shows credentials sent to an unrelated recipient.
- Uninstall’s package behavior is invoked through the CLI and handles package-owned configuration.
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@0.9.162.
See all versions of @theronap/cortex-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/cortex-mcp@0.9.162 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.