character-design
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE] (SAFE): The skill consists entirely of markdown instructions and YAML metadata. No executable scripts (Python, JavaScript, Shell) or configuration files for package managers were found.
- [PROMPT_INJECTION] (SAFE): The instructions set a specific persona and behavioral guidelines for character design. No attempts to bypass safety filters, extract system prompts, or override core instructions were detected.
- [Indirect Prompt Injection] (SAFE): The skill references local files (patterns.md, sharp_edges.md, validations.md) for domain knowledge. 1. Ingestion points: referenced markdown files. 2. Boundary markers: absent. 3. Capability inventory: none (no dangerous tools or actions available). 4. Sanitization: absent. The risk is negligible as the skill lacks exploitable capabilities.
Audit Metadata