specialist-design-brand-guardian
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that interpolates user-provided text directly into a sub-agent prompt, creating a potential surface for indirect instructions.
- Ingestion points: The
{the user's question}variable inSKILL.mdaccepts arbitrary user input. - Boundary markers: The prompt string
Answer: {the user's question}lacks delimiters or protective framing to distinguish instructions from data. - Capability inventory: The skill is designed to invoke the
Agenttool for task delegation. - Sanitization: No sanitization or filtering of the user input is specified within the skill instructions.
Audit Metadata