log-quality-issues

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Indirect Prompt Injection (LOW): The skill processes data from the /check-quality primitive and interpolates it into gh issue create commands. This creates an attack surface where malicious audit findings could influence the content of created issues.
  • Ingestion points: Findings returned by the /check-quality skill referenced in SKILL.md.
  • Boundary markers: None explicitly used during interpolation into the --title flag.
  • Capability inventory: Execution of gh CLI commands in SKILL.md.
  • Sanitization: The implementation uses a quoted heredoc ('EOF') for the issue body, which prevents variable expansion, but does not sanitize the --title flag against malicious content from the findings.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:26 PM