openclaw-small-bugfix-sweep

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from GitHub issues and pull requests, which creates a surface for indirect prompt injection attacks.
  • Ingestion points: The workflow uses the gh CLI in steps 1 and 3 of the 'Loop' section to read issue/PR bodies, comments, and linked references.
  • Boundary markers: No specific delimiters or safety instructions are defined to separate untrusted external content from the agent's internal instructions.
  • Capability inventory: The skill is capable of modifying local files and executing "gates" (tests/build scripts).
  • Sanitization: There is no evidence of automated sanitization or filtering for the external data being processed.
  • Mitigation: The risk is mitigated by the mandatory 'Peter Review Gate,' which explicitly forbids committing, pushing, or publishing changes without direct human confirmation of the specific diff.
  • [COMMAND_EXECUTION]: The skill instructions include the use of the GitHub CLI (gh) and the execution of local test gates. These are standard operations for a coding-assistance skill and are scoped to the intended purpose of bug fixing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 02:11 PM
Security Audit — agent-trust-hub — openclaw-small-bugfix-sweep