game-art-direction
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to ingest content from external files, which could potentially contain hidden or malicious instructions.
- Ingestion points: The skill reads
GAME_DESIGN.mdandPRODUCT_BRIEF.mdas context for generating art direction. - Boundary markers: There are no explicit delimiters or specific instructions for the agent to ignore potentially malicious embedded prompts within these input files.
- Capability inventory: The skill's primary capabilities are reading markdown files and writing output to
design/ART_DIRECTION.mdanddesign/VISUAL_TARGETS.md. It does not have access to network tools, shell execution, or system-level APIs. - Sanitization: The skill does not implement sanitization or validation for the content ingested from the design documents.
Audit Metadata