pr-description
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (gh) to view, create, and edit pull requests. These operations are within the stated scope of the skill's functionality.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted repository data to generate PR descriptions. 1. Ingestion points: Repository diffs and existing PR bodies (SKILL.md). 2. Boundary markers: Absent; there are no specific delimiters to isolate the diff content from the agent's instructions. 3. Capability inventory: Uses gh pr create and gh pr edit to perform network operations and modify pull requests (references/attachment-links.md). 4. Sanitization: The script check_attachment_urls.py validates URLs in the output, but no sanitization is performed on the input diffs.
- [SAFE]: The included Python script check_attachment_urls.py performs static analysis of Markdown files to identify temporary or signed URLs. It uses standard libraries and does not perform network operations or unsafe subprocess calls.
Audit Metadata