html-plan
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions and configuration contain no malicious patterns, obfuscation, or unauthorized data access behaviors. The skill is designed to produce responsive, accessible HTML documents with inline styles and scripts, specifically avoiding external network dependencies.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes external source material. 1. Ingestion points: The skill reads conversation history, project instructions, and supplied plans (SKILL.md). 2. Boundary markers: No specific delimiters are defined to separate user data from instructions. 3. Capability inventory: The skill generates HTML, CSS, and JavaScript. 4. Sanitization: No explicit sanitization or filtering of the source material is mentioned. This finding is assessed as safe given the restricted output format and directives to avoid external services.
Audit Metadata