pb-merge-conflicts
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions involve executing standard version control and development tools (git, uv, ruff, pytest). These are necessary for the skill's primary purpose of resolving code conflicts and verifying the resulting state.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it reads git commit messages and PR references which are external, potentially untrusted data sources.
- Ingestion points: Git commit logs and PR/issue references accessed via
git logand external links. - Boundary markers: Not present; the agent is instructed to read these sources directly to understand intent.
- Capability inventory: Local shell execution for git operations and test runners (
uv run) specified inSKILL.md. - Sanitization: No explicit sanitization or filtering of commit message content is performed before the agent processes the information.
Audit Metadata