theme-factory
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
- [Prompt Injection] (LOW): Indirect Prompt Injection surface detected. The skill's core purpose is to style untrusted artifacts (slides, documents), which could contain malicious instructions designed to influence agent behavior. 1. Ingestion points: SKILL.md (styling instructions for external artifacts). 2. Boundary markers: Absent. 3. Capability inventory: No executable scripts are included in the skill. 4. Sanitization: None specified for artifact content.
- [No Code] (SAFE): No executable files, command execution patterns, or system calls were identified within the skill package.
Audit Metadata