github-ops
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the GitHub CLI (
gh) to perform repository management tasks, including editing issues, commenting, managing releases, and interacting with the GitHub API. This is the intended primary functionality of the skill. - [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks (Category 8) because it processes external, untrusted content from GitHub issues, pull request descriptions, and CI logs.
- Ingestion points: Untrusted data enters the context via
gh issue list,gh pr view, andgh run view --log-failedcommands as described inSKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the ingested external data.
- Capability inventory: The skill has the capability to write back to GitHub via
gh issue edit,gh issue comment,gh release create, andgh run rerun. - Sanitization: There are no explicit sanitization or validation steps mentioned for the ingested data before it is processed or used to generate responses.
Audit Metadata