qa
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill ingests untrusted data from users to generate GitHub issues, creating a surface for indirect prompt injection.\n
- Ingestion points: User-provided problem descriptions are processed and used to populate issue templates in SKILL.md.\n
- Boundary markers: No explicit delimiters or instructions are used to separate user-provided content from the agent's logic.\n
- Capability inventory: The skill uses
gh issue createto write to external repositories and uses an internal subagent for codebase exploration.\n - Sanitization: The skill relies on natural language instructions (e.g., 'No file paths or line numbers') to mitigate data leakage rather than programmatic filtering or validation.\n- [COMMAND_EXECUTION]: The skill executes the GitHub CLI tool (
gh) to create durable issue records based on user input.
Audit Metadata