design-an-interface
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its sub-agent orchestration workflow.
- Ingestion points: User-provided module descriptions and requirements are captured in Step 1 and interpolated directly into sub-agent prompts in Step 2 of
SKILL.md. - Boundary markers: The prompt template lacks explicit delimiters (like XML tags or triple quotes) or 'ignore embedded instructions' warnings for the interpolated
[module description]and[gathered requirements]fields. - Capability inventory: The skill uses the
Tasktool to spawn multiple sub-agents, providing a mechanism for an attacker to potentially influence these agents if they provide malicious input as a module description. - Sanitization: There is no evidence of validation, escaping, or filtering of the external content before it is processed by the sub-agents.
Audit Metadata