adhd-design-expert

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The design workflow involves fetching external research which creates a potential surface for indirect prompt injection.\n- Ingestion points: The skill utilizes mcp__firecrawl__firecrawl_search to ingest data from various web sources during the research phase.\n- Boundary markers: There are no clear boundaries or instructions defined to prevent the agent from following directions that might be hidden in external design studies.\n- Capability inventory: With permissions for Write and Edit, the agent could potentially alter project files based on untrusted search results.\n- Sanitization: The skill does not define any steps for the validation or sanitization of content retrieved from the web.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 12:18 AM
Security Audit — agent-trust-hub — adhd-design-expert