file-pr
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository, including git diffs, pull request templates, and historical PR data, which could contain malicious instructions designed to influence the agent's behavior during PR description generation.
- Ingestion points: Repository task files, staged/unstaged changes, pull request templates, and merged PR history (referenced in SKILL.md).
- Boundary markers: The instructions do not specify the use of delimiters or boundary markers to isolate untrusted repository content from the agent's instructions.
- Capability inventory: The skill depends on the
commit-pushskill for git operations and uses REST/GraphQL APIs to create or update pull requests. - Sanitization: The workflow includes a manual instruction to check text and attachments for private data, but there is no explicit sanitization for embedded prompt instructions in the ingested data.
- [NO_CODE]: The skill consists exclusively of markdown instructions and YAML configuration files. No executable scripts (e.g., Python, JavaScript, Shell) are included in the skill package.
Audit Metadata