game-ai-assets

Pass

Audited by Gen Agent Trust Hub on Nov 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external URLs and local files, creating a surface for potential instruction injection.\n
  • Ingestion points: The skill uses WebFetch to retrieve license terms from vendor websites and reads local files such as design/ai-asset-log.md and project bibles.\n
  • Boundary markers: The instructions do not specify the use of delimiters or specific instructions to the agent to ignore embedded directives in the ingested content.\n
  • Capability inventory: The skill is permitted to use Bash for media processing and has the ability to write and edit files.\n
  • Sanitization: No explicit data sanitization or validation steps are defined for content retrieved from external sources before it is interpreted by the agent.\n- [EXTERNAL_DOWNLOADS]: The skill references and recommends the installation of specific third-party tools from well-known registries.\n
  • Evidence: The documentation in references/post-processing.md suggests installing @gltf-transform/cli@4.5.1 from the npm registry for asset optimization.\n- [COMMAND_EXECUTION]: The skill configuration utilizes shell commands to perform legitimate asset transformation tasks.\n
  • Evidence: The SKILL.md file defines allowed-tools that include Bash execution for standard utilities such as ffmpeg, magick, and gltf-transform to handle audio and image processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 7, 2026, 11:58 AM