gh-pr-publish
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses Git and GitHub CLI (gh) commands to manage source code and pull requests. All operations are standard for the described purpose, including branch management, status checks, and PR lifecycle management.
- [DATA_EXFILTRATION]: The skill interacts with GitHub via the
ghtool. This is the intended purpose of the skill and involves pushing code and metadata (titles, bodies) to the user's configured GitHub repository. - [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface as it reads information from existing pull requests, repository metadata, and git logs. While this data could theoretically contain malicious instructions, the risk is mitigated by the structured workflow and the requirement for user confirmation before executing significant actions based on that data.
- [SAFE]: The skill explicitly restricts its tool access to
gitandghvia theallowed-toolsconfiguration, minimizing the risk of unauthorized tool usage.
Audit Metadata