interaction-flows
Pass
Audited by Gen Agent Trust Hub on Jul 19, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script located at
../../scripts/validate_design_output.pyto ensure the generatedui-flows.mdfile meets the project's quality standards. This execution is part of the tool's intended internal validation process. \n- [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface by ingesting external data during the design process. \n - Ingestion points: Feature descriptions provided by the user and the content of
docs/loom/PRINCIPLES.md. \n - Boundary markers: None; the skill does not use specific delimiters to separate user input or project guidelines from its own internal logic. \n
- Capability inventory: The skill can write files to the local disk and execute a validation script. \n
- Sanitization: No explicit sanitization or input validation is mentioned for the ingested text.
Audit Metadata