codegen-diagram
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and processing of untrusted data from the user's local project files, creating an attack surface for indirect prompt injection.\n
- Ingestion points: Source code, SQL schemas (e.g., schema.sql), and ORM models are accessed to extract metadata for diagrams, as specified in reference/data-structure.md and reference/er-diagram.md.\n
- Boundary markers: The instructions lack explicit delimiters or warnings for the agent to ignore any natural language instructions that might be embedded in code comments or documentation within the analyzed files.\n
- Capability inventory: The skill directs the agent to read local files, analyze their structure, and generate structured Draw.io XML files.\n
- Sanitization: The instructions do not include requirements for validating or sanitizing the data extracted from the project files before processing.
Audit Metadata