game-asset-production
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines a production pipeline for game sprites and animations, delegating execution to the
fal-mediaMCP tool. It does not perform sensitive file access, network exfiltration, or privileged command execution. References to AI endpoints (fal-ai,openai) inassets/plan.jsonare consistent with the skill's stated purpose and use standard providers. - [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to read an external production plan guide (
../genmedia/references/production-plans.md) and retrieve published guides via thefal-mediatool. This creates a surface where instructions embedded in those external files could influence the agent's behavior. * Ingestion points: Local file reference inSKILL.mdand dynamically retrieved guides via thefal-mediatool. * Boundary markers: No delimiters or explicit instructions to ignore embedded commands are present. * Capability inventory: Media generation, image editing, and asset processing (matting, slicing). * Sanitization: No sanitization or validation of the external guide content is specified.
Audit Metadata