ia
Pass
Audited by Gen Agent Trust Hub on May 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data such as service plans, PRDs, and product ideas, which introduces a surface for indirect prompt injection.
- Ingestion points: User-provided service planning documents, product requirement documents (PRDs), or startup ideas (SKILL.md).
- Boundary markers: The instructions do not define clear delimiters or protective instructions to separate untrusted user input from the core task logic.
- Capability inventory: The skill utilizes file-writing capabilities to create and save the
SCREENS.mddocument in the current working directory. - Sanitization: No input validation, escaping, or sanitization mechanisms are implemented to handle potentially malicious content within the processed documents.
Audit Metadata