studio-design-identity-creator

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied documentation to inform its analysis and output content. * Ingestion points: Reads from docs/PRODUCT.md and docs/LAUNCHES.md (SKILL.md). * Boundary markers: The skill does not define explicit delimiters or isolation instructions for processing these files. * Capability inventory: Performs live web research and writes output back to productos/design/1-Product-Identity.md (SKILL.md). * Sanitization: No specific content sanitization or escaping mechanisms are mentioned for the ingested data.
  • [EXTERNAL_DOWNLOADS]: The skill performs live web research to gather competitive intelligence and check domain availability. This network activity is a primary feature of the brand strategy workflow and is consistent with the skill's stated purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 10:33 PM
Security Audit — agent-trust-hub — studio-design-identity-creator