@theronap/cortex-mcp@0.9.147
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 2mo ago · by lpm-firewall-aiThe package is not an install-hook malware package because its manifest has no automatic lifecycle script and its modifications require explicit CLI setup. Its broad recurring agent-hook, remote-skill, and session-upload behavior remains a real extension lifecycle risk that warrants a warning.
Decision evidence
public snapshot- Explicit setup installs stop, session-start, and prompt hooks and adds MCP allow rules.
- The capture hook posts session-derived content with its bearer token to the Agnoclast API.
- Session-start repair downloads organization-supplied skill bodies and writes them into detected agent skill directories.
- The Antigravity adapter writes a launchd plist and executable sync script.
- package.json has no preinstall, install, or postinstall lifecycle hook.
- Configuration changes are reached through explicit setup or install CLI commands, not package installation.
- The network base defaults to the package-aligned agnoclast.com host.
- Capture applies credential-shaped-string redaction before building its fallback transcript payload.
Source & flagged code
6 flaggedThis package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
lib/capture.mjsView on unpkgPackage source references weak cryptographic algorithms.
lib/capture.mjsView on unpkg · L1Findings
Affected versions and remediation
This report applies to @theronap/cortex-mcp@0.9.147.
See all versions of @theronap/cortex-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/cortex-mcp@0.9.147 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.