vois-loop
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill performs an automated validation pass by executing a local Node.js script (detect.mjs) located within the Vois design system's skill directory. This script is used to mechanically check generated files for compliance with design system rules.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (Category 8) because it is designed to ingest and process untrusted external data, such as feature tickets or project briefs.
- Ingestion points: Raw input, tickets, and briefs are ingested in Step 1 through the design-ask skill.
- Boundary markers: No explicit boundary markers or 'ignore embedded instructions' warnings are defined for the input content.
- Capability inventory: The skill has the capability to execute a local Node.js script on the file system.
- Sanitization: No specific sanitization or escaping of external content is mentioned; the skill relies on the design-ask sub-skill to unpack and frame requirements.
Audit Metadata