@theronap/agnoclast-mcp@0.9.187
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 source shows first-party agent integration that can extend agent behavior after explicit setup, supporting a warning. The manifest has no install lifecycle hook, and the inspected code does not establish malicious behavior.
Decision evidence
public snapshot- package.json defines the CLI entry point and has no npm lifecycle hooks.
- The editor adapters detect existing Codex and Cursor configurations; Cursor is described as capture-only.
- Setup installs bundled and organization-published skills into agent CLI directories.
- The uninstall command targets Agnoclast-managed agent configuration and hook files.
- Antigravity setup writes a launch-agent plist and sync script but does not activate the watcher; activation requires a separate user command.
- The CLI routes setup through an explicit command, and that setup performs agent integration.
- The package has no preinstall, install, or postinstall hook.
- Antigravity setup reports that its sync depends on a local development checkout, and does not load the launch agent itself.
- The inspected source does not establish credential theft or an active attack.
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/agnoclast-mcp@0.9.187.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.187 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.