pixel-art-sprites
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill analyzes external user code to validate pixel art rendering and configuration, creating a potential ingestion point for untrusted instructions. 1. Ingestion points: User codebase files matching the globs in references/validations.md. 2. Boundary markers: Absent; there are no explicit instructions for the agent to ignore prompt-like content inside the analyzed files. 3. Capability inventory: Limited to textual validation feedback; no subprocess execution, network operations, or file-writing capabilities were detected. 4. Sanitization: Absent.
- [Prompt Injection] (SAFE): The instructional grounding in SKILL.md, including directions to prioritize local reference files over generic knowledge, is appropriate for a specialized domain and does not constitute a safety filter bypass.
Audit Metadata