to-issues
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
ghCLI commands to interact with GitHub issues, including creating, viewing, listing, and editing issues. It also runsgit remote -vto identify the repository context automatically.\n- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests data from GitHub issue descriptions and comments which are potentially attacker-controlled.\n - Ingestion points: Issue content and comments are fetched in the 'Gather context' step and 'Issue tracker: GitHub' section using
gh issue viewandgh issue list.\n - Boundary markers: None. The skill does not use specific delimiters or instructions to ignore embedded commands in fetched content.\n
- Capability inventory: The skill can create, edit, and comment on GitHub issues using the
ghCLI.\n - Sanitization: None. The fetched content is processed directly to generate new issue descriptions.
Audit Metadata