generate-design-md
Pass
Audited by Gen Agent Trust Hub on Apr 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (Category 8) as it processes untrusted HTML and CSS from user-specified URLs.
- Ingestion points: The skill fetches external content using the
web_fetchtool as described inSKILL.md. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present to protect the agent from instructions hidden in fetched data.
- Capability inventory: The skill instructions include writing to the local file system to save the generated DESIGN.md file.
- Sanitization: No content sanitization or validation is performed on the data retrieved from external sources before it is analyzed and used to generate output.
Audit Metadata