kata-scope
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided inputs such as rough requests and idea briefs to generate structured work briefs. This ingestion of external data constitutes a potential attack surface for indirect prompt injection.
- Ingestion points: Processes 'rough-request', 'understood-context', 'idea-brief', and 'product-contract' from user input (SKILL.md).
- Boundary markers: The instructions do not specify explicit delimiters or 'ignore embedded instructions' markers for the processed content.
- Capability inventory: The skill environment is strictly limited to read-only access and local file writing. It explicitly prohibits remote operations, code execution, and system changes (SKILL.md).
- Sanitization: No specific input validation or sanitization mechanisms are described for the incoming work requests.
Audit Metadata