git-merge-expert
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from multiple sources which could contain malicious instructions designed to influence the agent's behavior during merge or conflict resolution tasks.
- Ingestion points: The $request argument, as well as output from external tools like gh pr view, git status, and git diff (SKILL.md, Step 0 and Step 1).
- Boundary markers: The instructions do not define clear delimiters or 'ignore embedded instructions' warnings for data processed from the working tree or GitHub API.
- Capability inventory: The skill has access to powerful tools including Bash for shell command execution, and Write/Edit for file system modification (SKILL.md, frontmatter).
- Sanitization: There is no mention of escaping, validation, or filtering of content retrieved from PR descriptions or commit messages before it is processed by the agent.
Audit Metadata