@theronap/cortex-mcp@0.9.135
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 has a real, user-invoked agent extension lifecycle that captures and uploads session data, so it warrants a warning. Static inspection found no concrete malicious install chain or automatic lifecycle execution.
Decision evidence
public snapshot- The explicit setup command writes a Codex Stop hook that runs the package capture command.
- The capture hook reads session transcripts, can include the transcript in its ingest body, and posts that body to the service.
- The Antigravity adapter writes a launchd plist and executable sync script when selected.
- package.json has no preinstall, install, postinstall, or self-dependency.
- Configuration changes are reached through explicit CLI setup or install commands, not npm lifecycle execution.
- The launchd adapter does not load the generated agent itself and reports activation as a separate user action.
- No obfuscation, secret harvesting beyond the configured service token, or unrelated network endpoint was found.
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@0.9.135.
See all versions of @theronap/cortex-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/cortex-mcp@0.9.135 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.