gh-issue-report
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the GitHub CLI (
gh) to automate repository tasks such as listing issues, fetching repository labels, and creating new reports. These shell commands include variable interpolation for repository paths and search terms. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external GitHub repositories, presenting an indirect prompt injection surface.
- Ingestion points: The skill reads repository source code, issue templates, and contributing guidelines via
gh apiandgh issue list(SKILL.md, Steps 4, 6, 8, and 9). - Boundary markers: A human-in-the-loop verification step is enforced in Step 13, requiring the user to review and approve the drafted issue before the
gh issue createcommand is executed. - Capability inventory: The skill possesses the capability to read local and remote files and perform write operations on GitHub repositories.
- Sanitization: The workflow relies on manual user inspection to ensure the drafted content is accurate and safe before submission.
- [EXTERNAL_DOWNLOADS]: The skill fetches repository metadata and documentation from the GitHub API. These network operations target a well-known service and are consistent with the skill's stated purpose of filing GitHub issues.
Audit Metadata