@theronap/agnoclast-mcp@0.9.235
Connect your AI assistant to Cortex — your org's projects, activity, gaps, and directives, scoped to you.
AI Security Review
scanned 19d ago · by lpm-firewall-aiThe manifest contains no npm lifecycle hooks, and the reviewed configuration and persistence behavior is tied to explicit CLI setup or install actions. The flagged uninstall and transcript-tracking code is consistent with removing managed integration and reading the active session's files.
Decision evidence
public snapshot- package.json exposes a CLI and has no preinstall, install, or postinstall hook.
- The CLI dispatches setup, install, and uninstall as explicit commands. Antigravity wiring writes a shell script and launchd plist; the source says launchd activation is left to the user.
- Codex and Cursor adapters describe their integration capabilities and configuration destinations.
- Setup writes agent configuration, and skills installation targets detected Claude Code and Codex directories.
- Uninstall targets the package's own MCP entries and hooks; working_files reads the current session's transcript to track changed files.
- No inspected source established a concrete attack surface.
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/agnoclast-mcp@0.9.235.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.235 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.