dramagic-character-art
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a structured workflow for creating consistent character sprites, full-body images, and avatars. A thorough analysis of the instructions found no evidence of prompt injection, data exfiltration, obfuscation, or unauthorized access attempts.
- [INDIRECT_PROMPT_INJECTION]: The skill involves ingesting external data through image search and generation results. While this represents a potential ingestion surface, the instructions focus purely on visual consistency and technical specifications (WebP format, alpha channels, alignment) rather than processing untrusted text that could influence agent behavior.
- [DYNAMIC_EXECUTION]: The instructions permit the creation of local processing code to fulfill deterministic needs if standard host tools fail. This is a common pattern for automating image manipulation tasks (such as format conversion or transparency repairs) and does not involve executing code from untrusted remote sources.
Audit Metadata