git-issue
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill handles untrusted data from GitHub issue titles and bodies, representing a potential indirect prompt injection surface. Evidence includes:
- Ingestion points: Data retrieved via
gh issue view(Step 2). - Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands in issue content.
- Capability inventory: The agent has permissions for file writing, shell execution, and pull request creation.
- Sanitization: No specific filtering or validation of the fetched issue content is performed.
- [COMMAND_EXECUTION]: The skill employs dynamic shell execution for environment discovery and workflow automation.
- Dynamic context injection: Uses
!git remote -v,!git branch --show-current, and!git status --porcelain=v2at load time to populate repository metadata. - Automation tools: Orchestrates complex tasks using Git, the GitHub CLI, and pre-commit hooks to facilitate the TDD lifecycle.
Audit Metadata