skill-monitor

Pass

Audited by Gen Agent Trust Hub on Apr 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to read observational signals from local files (e.g., .claude/session-metrics/metrics.jsonl) and generate a dashboard. This is a standard developer workflow and does not involve risky operations.
  • [SAFE]: No network activity was detected. The skill does not use any tools for external communication or data exfiltration.
  • [SAFE]: The skill uses a 'disable-model-invocation' configuration, which is a platform-level constraint that limits the model's ability to trigger further actions, reducing the overall attack surface.
  • [SAFE]: File system operations are restricted to specific, non-sensitive directories related to the skill's purpose (local metrics and dashboards).
  • [SAFE]: There is no evidence of obfuscation, dynamic code generation, or attempts to bypass security controls.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 19, 2026, 04:30 PM
Security Audit — agent-trust-hub — skill-monitor