game-design-review
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external content such as game design documents and playtest observations. This creates an attack surface where malicious instructions embedded in those documents could potentially influence the agent's analysis or the behavior of sub-agents.
- Ingestion points: The skill ingests user-provided game design objects and documents as the primary source for its review modes in
SKILL.md. - Boundary markers: The instructions do not specify the use of clear boundary markers or protective delimiters when the agent handles or transmits user-supplied design text.
- Capability inventory: The skill includes instructions for delegating sub-tasks to other agents, which expands the potential impact of an injection by allowing it to propagate through a multi-agent chain.
- Sanitization: There are no documented steps for sanitizing or filtering the external content before it is analyzed or used to brief sub-agents.
Audit Metadata