specialist-design-visual-storyteller
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions and configuration do not contain any malicious patterns, obfuscation, or unauthorized access attempts. All operations are confined to standard agent delegation tools.
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by interpolating user input directly into a sub-agent prompt.
- Ingestion points: The
{the user's question}variable inSKILL.mdaccepts untrusted user input. - Boundary markers: No explicit delimiters or boundary instructions are used to isolate the user input within the sub-agent prompt.
- Capability inventory: The skill uses the
Agenttool to spawn sub-agents but does not perform file system or network operations itself. - Sanitization: No sanitization or filtering of the user input is performed before interpolation. This is considered low risk as it is the intended primary purpose of the skill.
Audit Metadata