git-workflow
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection by processing untrusted data while maintaining write capabilities.
- Ingestion points: The skill directs the agent to inspect git status, diffs, and submodule states (SKILL.md).
- Boundary markers: No delimiters or protective instructions are used to separate the instructions from the data in the diffs.
- Capability inventory: The skill instructs the agent to perform git add, commit, and push operations using its built-in tools.
- Sanitization: No sanitization or validation logic is present to filter malicious instructions within the tracked files or diffs.
Audit Metadata