@theronap/agnoclast-mcp@0.9.241
Connect your AI assistant to Cortex — your org's projects, activity, gaps, and directives, scoped to you.
AI Security Review
scanned 18d ago · by lpm-firewall-aiThe manifest has no automatic install hook, and the flagged configuration and persistence behavior is tied to user-run integration commands. The inspected runtime and helper sources did not establish a concrete attack.
Decision evidence
public snapshot- The manifest defines no install lifecycle hook; its scripts are release, promotion, and rollback commands.
- The CLI reaches setup and uninstall through explicit subcommands. Setup requires a supplied token before writing configuration.
- Codex and Cursor integrations target their own configuration directories; skills are installed only for detected agent clients.
- The uninstall code removes managed entries from named configuration files and filters only the package’s tool namespaces.
- Antigravity wiring writes a script and launch agent file, but requires a separate manual activation step.
- The working-files helper locates the current session’s transcript; inspected sources establish no attack behavior.
- Scanner hints flag agent configuration writes and persistence, but inspected code ties them to explicit setup or install actions; Antigravity’s watcher is not activated by the package code.
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@0.9.241.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.241 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.