game-creative-director
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from project files (such as vision documents, Game Design Documents, and project decision logs) which could contain malicious instructions if the files are from an untrusted source.
- Ingestion points: The agent reads project documentation and GDD sections using file discovery and reading tools as part of its 'Audit existing vision materials' workflow step.
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the files being read.
- Capability inventory: The skill has the capability to write and edit files in the project directory based on its analysis of ingested data. It also includes the
AskUserQuestiontool, which can serve as a human-in-the-loop safeguard for significant decisions. - Sanitization: There are no explicit sanitization or validation procedures mentioned for data retrieved from the project filesystem before it is used to generate new file content or perform actions.
Audit Metadata