gh-draft-pr
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses local CLI tools, specifically 'git' and 'gh', to gather branch information, commit history, and to execute the final pull request creation command.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the way it processes external data.
- Ingestion points: The skill ingests untrusted data from 'git log' (commit messages) and branch names (e.g., tickets) to populate the PR template.
- Boundary markers: No specific boundary markers or 'ignore' instructions are provided to separate user-provided commit data from the skill's own instructions.
- Capability inventory: The skill can write files to the local workspace (e.g., .pr-body-draft.md) and execute GitHub CLI commands.
- Sanitization: The skill does not perform sanitization or validation of the commit messages before using them to generate the PR title or body content.
Audit Metadata