entertainment

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS] (LOW): The skill performs HTTP GET requests to the non-whitelisted domain 60s.viki.moe to fetch content.
  • [INDIRECT_PROMPT_INJECTION] (LOW): The skill possesses a surface for indirect prompt injection by displaying untrusted data from an external API. \n
  • Ingestion points: API responses from https://60s.viki.moe/v2/ endpoints including Hitokoto and Duanzi. \n
  • Boundary markers: Absent; the content is directly displayed to the user without delimiters. \n
  • Capability inventory: No dangerous system capabilities or command execution; limited to network reads and saving one image file (moyu.jpg). \n
  • Sanitization: None; the skill assumes the API provider is trustworthy.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:39 PM