@theronap/cortex-mcp@0.9.134
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-aiNo npm lifecycle hook or covert install-time execution was found. The package nevertheless performs explicit-user-command AI-agent configuration, automated capture, and network transfer, so it warrants a warning for dangerous extension capability.
Decision evidence
public snapshot- The explicit install command wires every selected AI editor and records a capability manifest.
- Claude settings receive automatic Stop, SessionStart, and prompt-submission commands that run this package through npx.
- The capture hook reads a session transcript, builds an ingest body, and posts it with the configured token.
- The Antigravity adapter writes a launchd plist and executable watcher script, though it does not load the agent.
- package.json has no preinstall, install, or postinstall lifecycle hook.
- The configuration and hook changes are reachable through explicit CLI setup or install commands, not package installation or import.
- The observed network destination is the package-aligned Agnoclast service; no unrelated exfiltration endpoint or opaque payload loader was found.
- The launchd artifact is not activated by the package and its generated script exits if its local prerequisite is absent.
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@0.9.134.
See all versions of @theronap/cortex-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/cortex-mcp@0.9.134 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.