qa
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. It ingests arbitrary user descriptions and codebase content to generate and execute GitHub CLI commands.
- Ingestion points: User bug descriptions provided during the interactive session and codebase data (such as UBIQUITOUS_LANGUAGE.md) read by the background subagent.
- Boundary markers: The instructions do not define clear delimiters or include 'ignore embedded instructions' warnings for the data being processed.
- Capability inventory: The skill uses the 'gh issue create' command to perform network-based write operations to external repositories.
- Sanitization: The skill lacks technical sanitization for user input and explicitly instructs the agent to skip user review before filing issues ('Do NOT ask the user to review first'), which removes a manual verification step that could intercept malicious payloads.
Audit Metadata