adhd-design-expert

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill is designed to ingest data from untrusted external sources, which creates a surface for potential indirect instructions.\n
  • Ingestion points: Untrusted data enters the agent context via the mcp__firecrawl__firecrawl_search tool and the Read tool for accessing file content.\n
  • Boundary markers: The instructions do not include explicit delimiters or safety prompts to ignore instructions embedded in the processed data.\n
  • Capability inventory: The skill possesses significant capabilities including Write, Edit, and mcp__magic__21st_magic_component_builder, which could be targeted by a successful injection.\n
  • Sanitization: No explicit sanitization or validation of external content is specified in the skill's logic or design workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 08:32 AM