specialist-game-development-game-designer
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the interpolation of untrusted user content into instructions for a sub-agent, creating a surface for potential injection attacks. Ingestion points: User content is inserted via the
{the user's question}placeholder inSKILL.md. Boundary markers: Absent; there are no delimiters (such as XML tags or quotes) to distinguish user input from the specialist's instructions. Capability inventory: The skill leverages theAgenttool to create sub-agents with specific design capabilities. Sanitization: No validation or sanitization is performed on the user-provided data before it is processed.
Audit Metadata