diagram
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches a JSON validation schema from the vendor's website (todiagram.com) and queries the Iconify search API (api.iconify.design) to find appropriate icons for diagram components.
- [COMMAND_EXECUTION]: Instructs the agent to run a local script 'scripts/validate_todiagram_schema.py' to verify the structural integrity and canonical correctness of generated diagram files.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external diagram data and user-supplied notes, which presents a surface for indirect prompt injection. * Ingestion points: Processes user-provided architecture notes and existing ToDiagram JSON files via the schema-build and detail-calibration modes. * Boundary markers: No explicit delimiters or boundary instructions are used when processing external inputs. * Capability inventory: The skill has the ability to write files, execute a local Python script, and perform specific network requests. * Sanitization: Employs schema validation and canonical linting through the 'scripts/validate_todiagram_schema.py' script to ensure output data adheres to defined structures.
Audit Metadata