github-pr-fix
Pass
Audited by Gen Agent Trust Hub on Apr 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local shell commands for build verification and testing. It also utilizes the GitHub CLI (
gh) for repository management andgitfor pushing code changes to the active PR branch. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting untrusted content from GitHub PR comments and review threads.
- Ingestion points: PR metadata, file content, issue comments, and review threads are fetched via
gh pr viewandgh api(documented in SKILL.md and references/pr-fix-workflow.md). - Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between untrusted PR comments and system instructions.
- Capability inventory: The skill has the ability to perform
git push, post comments viagh api, and run arbitrary "verification commands" (e.g., tests/builds) in the local environment. - Sanitization: No sanitization or validation of the fetched PR content is specified before the agent processes the information.
Audit Metadata