@theronap/agnoclast-mcp@0.9.207
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 manifest has no install lifecycle hook, and agent configuration changes are reached through explicit setup commands. The inspected capture and editor code is consistent with the package’s integration purpose, with no concrete attack behavior established.
Decision evidence
public snapshot- package.json defines a CLI entrypoint and no install lifecycle hook.
- Setup is an explicit CLI command that writes agent configuration and capture hooks.
- Codex wiring checks for a Codex configuration directory; Cursor is capture-only and does not inject prompt context.
- Managed skills are installed only into detected Claude Code and Codex directories.
- Uninstall removes managed configuration entries; transcript lookup targets the current session ID.
- Antigravity writes configuration files but requires a separate activation step; capture code says the cloud receives derived summaries.
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@0.9.207.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.207 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.