gamedesigner-worflow
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements a messaging pipeline that reads task assignments from CLI arguments and local JSON files. This establishes an ingestion point for untrusted data that could potentially contain malicious instructions intended to manipulate the agent's behavior.
- Ingestion points: The
Standard Message PipelineandAgent Startup Protocolsections inSKILL.mddescribe reading from$arguments.message,pending-messages-gamedesigner.json, and themessages/directory. - Boundary markers: Absent. The instructions do not define delimiters or provide warnings to the agent to disregard instructions embedded within these data sources.
- Capability inventory: The skill grants the agent permission to write to the
docs/design/directory, invoke multiple sub-agents (gamedesigner-gdd-documenter,gamedesigner-thermite-facilitator, etc.), and utilize MCP tools for web searching and browser-based playtesting. - Sanitization: Absent. There is no mention of validating, escaping, or sanitizing the content of the messages before they are processed by the agent.
Audit Metadata