game-character-sprites
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill and its associated scripts perform legitimate image processing and validation tasks for game development. No malicious code, obfuscation, or persistence mechanisms were found.
- [INDIRECT_PROMPT_INJECTION]: The skill features an ingestion surface where user-supplied prompts and reference images influence the output of image generation tools and the content of manifest files.
- Ingestion points: User-provided text concepts and reference images are used in generation prompts (SKILL.md); the agent reads workspace files like
run-manifest.jsonandvisual-review.json(scripts/validate_run_manifest.py). - Boundary markers: The skill provides specific prompt templates to guide the image generation process and maintain consistency (SKILL.md).
- Capability inventory: The skill executes local Python scripts and performs file-write operations for images (PNG, GIF, WebP) and metadata (JSON) within the workspace (SKILL.md).
- Sanitization: The
validate_run_manifest.pyscript validates the structure and fields of the manifest to ensure data integrity. - [EXTERNAL_DOWNLOADS]: The skill relies on the
PillowPython package, a widely trusted and standard library for image manipulation (README.md).
Audit Metadata