skills/openclaw/skills/prompt-guard/Gen Agent Trust Hub

prompt-guard

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary purpose is defensive, providing filters and guardrails against common AI vulnerabilities.
  • [EXTERNAL_DOWNLOADS]: Fetches threat intelligence patterns from the HiveFence network, which is a vendor-operated service for collective security.
  • [DATA_EXFILTRATION]: Reports detected attack signatures to the HiveFence network to improve collective defense. This is a core advertised feature for sharing security metadata.
  • [COMMAND_EXECUTION]: Provides local scripts (detect.py, audit.py) for security management, which is expected behavior for a security utility.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 04:23 PM