smart-git-automation
Pass
Audited by Gen Agent Trust Hub on Jul 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands via 'git' and 'gh' CLI tools to manage repository state. This includes creating branches, staging files, and pushing code to remotes.- [PROMPT_INJECTION]: An indirect prompt injection surface exists as the skill processes untrusted filenames and file diffs which could contain malicious instructions designed to influence the agent's behavior. \n
- Ingestion points: SKILL.md (Step 1) reads data from 'git status' and 'git diff', including filenames and code content. \n
- Boundary markers: The skill instructions advocate for using '--' pathspec separators and '-z' NUL-delimited output to handle filenames safely. \n
- Capability inventory: Subprocess calls to 'git' and 'gh' for repository operations. \n
- Sanitization: Instructions explicitly warn against shell command concatenation and recommend manual confirmation steps.
Audit Metadata