pr-message
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions are focused entirely on document generation and formatting. No malicious patterns such as prompt injection, data exfiltration, or unauthorized command execution were found. The use of
disable-model-invocation: truein the frontmatter further restricts the agent from performing any actions beyond text generation, effectively neutralizing common attack vectors associated with processing untrusted data like commit messages.
Audit Metadata