Skills
Navigate
skills/immamdouhaboammar/get-fable/create-design-system/Gen Agent Trust Hub

create-design-system

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's core functionality involves ingesting data from external sources like Figma links and project codebases, which creates a surface where embedded malicious instructions could influence the agent.\n
  • Ingestion points: Uses get_design_context for Figma and local_ls or repl for codebase exploration.\n
  • Boundary markers: No delimiters or specific instructions to ignore embedded commands are defined for the ingestion of external data.\n
  • Capability inventory: The agent can write files and execute tools like repl and set_project_title.\n
  • Sanitization: No explicit sanitization or validation of data retrieved from external sources is performed.\n- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to link to well-known iconography services like Lucide or Heroicons via CDN if local assets are missing. These are trusted, well-known services and do not escalate the risk level.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 06:45 PM