html-diagram
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection by processing untrusted user input to generate executable HTML and JavaScript content.
- Ingestion points: User-provided system descriptions and flow data (SKILL.md).
- Boundary markers: The skill does not define specific delimiters to separate user data from instructions.
- Capability inventory: Generation of HTML files with inline CSS and JavaScript (SKILL.md).
- Sanitization: The instructions do not specify any validation or sanitization for input data.
- [SAFE]: The skill explicitly requires that diagrams be self-contained and forbids external services or build steps, which reduces the risk of remote code execution or data exfiltration (SKILL.md).
Audit Metadata