pr-to-main
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing external data from git commands without safety delimiters.
- Ingestion points: The skill reads data from
git status,git diff, andgit logas part of its analysis workflow defined inSKILL.md. - Boundary markers: Absent. There are no instructions to use delimiters or ignore instructions that may be embedded within the commit messages or code diffs.
- Capability inventory: The skill possesses the capability to perform network and write operations via
git pushandgh pr create, as specified inSKILL.md. - Sanitization: Absent. The skill does not perform any escaping, validation, or filtering of the ingested git data before incorporating it into the final PR generation.
Audit Metadata