html-diagram
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected. The skill defines formatting and logic for diagram generation.
- [SAFE]: The skill explicitly mandates that diagrams must be self-contained and require no external services, which significantly reduces the risk of data exfiltration or external dependency-based attacks.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it generates HTML and JavaScript based on user-provided descriptions. (1) Ingestion points: User-provided system or flow descriptions. (2) Boundary markers: No explicit markers defined in instructions for the agent to separate data from code. (3) Capability inventory: Generation of executable HTML, CSS, and JavaScript artifacts. (4) Sanitization: No explicit sanitization or escaping instructions are provided for handling user content within the generated code.
Audit Metadata