vp-git
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing data from external, potentially untrusted sources.
- Ingestion points: It reads local repository history, remote state, pull request threads, and external templates for
.gitignorefiles (SKILL.md,references/gitignore.md,references/pull-requests.md). - Boundary markers: No specific delimiters are prescribed to encapsulate untrusted data, making it possible for instructions embedded in commit messages or PR comments to be misinterpreted as system commands.
- Capability inventory: The skill possesses the ability to modify the repository, including committing changes, deleting branches or worktrees, and merging pull requests (
references/cleanup.md,references/commits.md). - Sanitization: The skill does not define any sanitization or validation logic for the text content it retrieves from Git history or GitHub APIs.
Audit Metadata