NYC

design-system-creator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • PROMPT_INJECTION (LOW): Indirect Prompt Injection surface through web search results.\n
  • Ingestion points: The skill uses the mcp__firecrawl__firecrawl_search tool to ingest data from external URLs during research tasks.\n
  • Boundary markers: There are no explicit instructions or delimiters for the agent to treat search data as untrusted or to ignore instructions found within retrieved content.\n
  • Capability inventory: The skill has permissions to Write and Edit local files, which could be exploited if the agent follows instructions embedded in search results to modify the project in an unsafe way.\n
  • Sanitization: The skill does not define any sanitization or validation process for content retrieved via the search tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:54 PM