file-pr
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from the user's prompt and current codebase state to populate PR fields.
- Ingestion points: Processes the user's original prompt to generate descriptions and utilizes codebase changes (via the
$show-meskill) to populate the changes and summary sections (SKILL.md). - Boundary markers: Absent. The instructions do not define delimiters or provide warnings to the agent to ignore instructions potentially embedded within the user prompt or codebase content.
- Capability inventory: The agent has the capability to create and submit new Pull Requests to the repository, including adding labels.
- Sanitization: Absent. The skill does not specify methods for escaping, validating, or filtering external content before it is interpolated into the PR structure.
Audit Metadata