git-workflow
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted data in the form of Git diffs and source code to generate commit messages and PR descriptions. It lacks specific instructions or delimiters to ignore or sanitize instructions that might be embedded within the code changes (such as in comments), which could allow an attacker to influence the generated descriptions.\n
- Ingestion points: Git diffs and source code content analyzed via the prompt in SKILL.md.\n
- Boundary markers: None identified to separate instructions from code data.\n
- Capability inventory: Generates commit messages, branch names, and PR description templates.\n
- Sanitization: No validation or sanitization of the processed code content is described.
Audit Metadata