pixel-art

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user input through instructions to generate custom visual content, creating a potential surface for indirect prompt injection.\n
  • Ingestion points: The $ARGUMENTS variable in SKILL.md is used to define the illustration requirements.\n
  • Boundary markers: None explicitly defined; user input is interpolated directly into the scene logic.\n
  • Capability inventory: The skill uses Write, Edit, Read, and Bash (for previewing files).\n
  • Sanitization: Not explicitly detailed in the generation workflow, though manual iteration and cleanup are suggested.\n- [SAFE]: The skill content consists of legitimate design guidelines and SVG code templates for pixel art. The tools requested are appropriate for the stated purpose of creating and viewing image files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 02:08 PM
Security Audit — agent-trust-hub — pixel-art