comment-writer
Pass
Audited by Gen Agent Trust Hub on May 10, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill instructions define a specific persona and formatting rules for developer collaboration. No malicious patterns, obfuscation, or bypass attempts were detected.
- [COMMAND_EXECUTION]: Includes a reference to
gh pr view, which is a legitimate tool for inspecting Pull Request metadata. The command is scoped to specific non-sensitive fields such as title and body. - [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes untrusted data from Pull Requests.
- Ingestion points: Pull Request title and body are fetched via the
gh pr viewcommand inSKILL.md. - Boundary markers: Absent; the skill does not explicitly instruct the agent to ignore instructions embedded within the fetched PR content.
- Capability inventory: Uses the GitHub CLI (
gh) for read operations. - Sanitization: Absent; the content is processed directly for comment generation.
Audit Metadata