uml-and-software-architecture-visualization
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, including PostgreSQL schemas, XMI files, BPMN XML, and various diagram DSLs (PlantUML, Mermaid), to generate visualizations.\n
- Ingestion points: Processes user-provided system descriptions, database schemas, and model files as identified in SKILL.md and references/formats-and-interchange.md.\n
- Boundary markers: The instructions do not explicitly define boundary markers (such as XML tags or specific delimiters) or include warnings for the agent to ignore instructions potentially embedded within the processed data.\n
- Capability inventory: The skill generates executable or renderable visualization code (Mermaid, PlantUML, TypeScript) and interacts with browser-based rendering stacks as described in references/typescript-web-rendering.md, which could be influenced by malicious instructions in the input.\n
- Sanitization: There are no explicit instructions for sanitizing or escaping the content of external files before processing or interpolating it into prompts.
Audit Metadata