pr-diff-writer
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from git diffs and commit history to generate pull request content. This represents an attack surface where malicious instructions embedded in code comments or commit messages could influence the agent's generated output.
- Ingestion points: Git commit history, file-level changes, and code diff hunks.
- Boundary markers: The workflow lacks explicit delimiters or instructions to treat diff content as data only, increasing the risk that the agent might follow instructions embedded within the diff.
- Capability inventory: The skill is authorized to produce natural language summaries, titles, and structured PR bodies.
- Sanitization: No sanitization or filtering of the input diff data is performed before it is analyzed for intent and content.
Audit Metadata