specialist-design-image-prompt-engineer
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted user input and passes it directly to a sub-agent without proper encapsulation or sanitization.
- Ingestion points: User input enters the system via the
{the user's question}variable inSKILL.md. - Boundary markers: The skill lacks boundary markers or delimiters to separate instructions from user-provided data when calling the sub-agent.
- Capability inventory: The skill utilizes the
Agenttool to delegate tasks to external specialized agent types. - Sanitization: There is no evidence of input validation or escaping before the user content is interpolated into the sub-agent's prompt.
Audit Metadata