@theronap/agnoclast-mcp@0.9.280
Connect your AI assistant to Cortex — your org's projects, activity, gaps, and directives, scoped to you.
AI Security Review
scanned 6d ago · by lpm-firewall-aiThe package automatically repairs a Claude Code control-surface hook during SessionStart, including re-adding it when absent. The guard has a package-related privacy purpose, but silently restoring a removed hook is an unrequested agent-configuration mutation, so this warrants a warning rather than a block.
Decision evidence
public snapshot- The `status` command is wired as a SessionStart health check and calls `healConfidentialGuard` automatically.
- The self-heal copies the guard and adds its PreToolUse hook to Claude settings when that hook is missing.
- The Antigravity adapter writes its artifacts only when wired and explicitly does not activate the launchd watcher.
- The guard is intended to block other Agnoclast connections in a session locked to a confidential brain.
- The Antigravity adapter warns that manual `launchctl load` is needed to activate its watcher.
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@0.9.280.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.280 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.