solar-duotone-bold

Warn

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [OBFUSCATION]: The file demo/index.html contains a large Base64-encoded string (encodedHtml) that hides the entire structure and logic of the reference design design demo.- [DYNAMIC_EXECUTION]: The skill dynamically decodes the encodedHtml variable using atob() and injects it into an iframe's srcdoc attribute, creating a runtime execution path that bypasses static analysis.- [EXTERNAL_DOWNLOADS]: The skill references and loads scripts and media from external sources, including cdn.tailwindcss.com, code.iconify.design, and a Supabase storage bucket (hoirqrkdgbmvpwutwuwj.supabase.co).- [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through its ingestion of external design data.
  • Ingestion points: demo/PROMPT.md directs the agent to treat the demo/index.html file and external Neuform.ai URLs as high-fidelity references for visual and interaction design.
  • Boundary markers: Absent. No instructions are provided to the agent to ignore or sanitize potentially malicious instructions embedded in the reference design source.
  • Capability inventory: The skill utilizes network fetching (fetch) and dynamic code execution (srcdoc and Base64 decoding).
  • Sanitization: Absent. The skill does not validate or sanitize the reference HTML content or fetched metadata before processing.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 26, 2026, 01:38 PM
Security Audit — agent-trust-hub — solar-duotone-bold