git-workflow
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the local environment, which could be manipulated by an attacker to influence the agent's behavior.
- Ingestion points: The skill instructs the agent to read
git status, file diffs, project-specificAGENTS.md, and repository PR templates. - Boundary markers: The instructions do not define clear delimiters or "ignore" directives to prevent the agent from following instructions potentially embedded within code diffs or project documentation.
- Capability inventory: The skill facilitates git operations such as branch creation, commit message generation, and pull request drafting.
- Sanitization: There is no evidence of sanitization or filtering applied to the repository data before it is processed by the agent to generate workflow suggestions.
Audit Metadata