gitflow
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from git history and pull request titles to generate project documentation, creating a vulnerability to indirect prompt injection.
- Ingestion points: The agent retrieves pull request subjects and commit messages via git logs to populate CHANGELOG.md and GitHub release highlights.
- Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore instructions that might be embedded in the ingested content.
- Capability inventory: The skill utilizes shell commands through git and gh and has the ability to write to files such as CHANGELOG.md and project manifests.
- Sanitization: The skill lacks logic for sanitizing or escaping content retrieved from external sources before incorporating it into the project files.
Audit Metadata