git-hero
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to analyze untrusted data from Git repositories to provide diagnostic help and workflow guidance.
- Ingestion points: The agent is instructed to use
git status,git reflog, andgit logto diagnose issues, which ingests branch names, commit messages, and other repository metadata (SKILL.md, references/scenarios.md). - Boundary markers: The instructions do not specify any delimiters or safety markers to differentiate between repository content and agent instructions.
- Capability inventory: The skill encourages the use of a wide range of Git commands, including history rewriting (
rebase,reset), remote synchronization (push), and configuration changes (references/commands.md, references/config-recipes.md). - Sanitization: There are no explicit requirements for the agent to sanitize repository output before processing it.
- [NO_CODE]: The skill consists entirely of Markdown reference materials and does not include any scripts, binaries, or automated execution files.
Audit Metadata