character-design
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a set of templates and workflows for visual character consistency, which is a standard creative task for AI agents.
- [SAFE]: External integrations are limited to routing requests to well-known and reputable AI model providers such as OpenAI, Fal.ai, ByteDance, xAI, and Veed.
- [SAFE]: File system interactions are limited to saving generated assets into a designated output directory (
./outputs/characters/). - [INDIRECT_PROMPT_INJECTION]: The skill uses user-provided text (Character Anchors) to build prompts. While this is an ingestion point for untrusted data, it is a core feature of the skill's intended functionality and does not present an unusual security risk in this context.
Audit Metadata