zg-lead-product-designer
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions and associated reference files do not contain any malicious patterns.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided inputs such as product descriptions and business data to generate design cards. While this represents a data ingestion surface, the skill lacks any dangerous capabilities (e.g., network access, file system writes, or shell execution), making the risk of exploitation negligible.
- Ingestion points:
SKILL.md(Necessary Input section) processes user files and text input. - Boundary markers: Explicit delimiters for untrusted data are not specified in the prompt.
- Capability inventory: No high-risk capabilities detected; output is limited to text generation.
- Sanitization: No specific sanitization or filtering logic is present for input data.
Audit Metadata