design-an-interface
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided module descriptions and requirements to generate instructions for sub-agents.
- Ingestion points: User input is directly interpolated into the sub-agent prompt template within
SKILL.md(e.g.,[module description],[gathered requirements]). - Boundary markers: The prompt template lacks explicit delimiters or "ignore instructions" warnings to isolate user data from the agent's logic.
- Capability inventory: The skill utilizes a task-spawning tool to orchestrate sub-agents but does not have access to sensitive capabilities such as the file system, network operations, or arbitrary command execution.
- Sanitization: There is no evidence of sanitization, filtering, or validation of user-supplied text before it is passed to the sub-agents.
Audit Metadata