game-world-design
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied external content (source bibles, concepts, and product briefs) to generate a game design document. This creates a surface where malicious instructions could be embedded in the processed data.
- Ingestion points: Instructions in
SKILL.mdrequire the agent to read and processSOURCE_BIBLE.md,CONCEPT.md, andPRODUCT_BRIEF.md. - Boundary markers: The skill does not define explicit delimiters or use specific instructions to ignore potentially conflicting commands within the input files.
- Capability inventory: The skill is restricted to generating a markdown document (
design/GAME_DESIGN.md) and lacks access to network tools, sensitive file paths, or shell execution. - Sanitization: No sanitization or input validation logic is prescribed for the external markdown content.
Audit Metadata