sn-search-social-cn

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: Authentication cookies for platforms like Zhihu and Douyin are handled via environment variables or CLI arguments, avoiding hardcoded secrets and following standard security practices.
  • [SAFE]: Network operations are directed solely at well-known social media platforms (Bilibili, Zhihu, Douyin) to perform search queries.
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection as it retrieves untrusted search results from external social media platforms. This is a common characteristic of search-oriented tools.
  • Ingestion points: External API responses processed in bilibili_search.py, douyin_search.py, and zhihu_search.py.
  • Boundary markers: Absent. No specific delimiters are used to wrap the untrusted content.
  • Capability inventory: Subprocess execution is not utilized; however, zhihu_search.py writes long content to temporary files.
  • Sanitization: The skill uses regular expressions to strip HTML tags from search results, providing a basic level of cleanup.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 09:37 AM