baidu-search

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Performs network requests to official Baidu infrastructure domains including qianfan.baidubce.com, appbuilder.baidu.com, and baike.baidu.com to retrieve search results and encyclopedia content.- [INDIRECT_PROMPT_INJECTION]: The skill handles untrusted content from external search results which could theoretically contain malicious instructions targeting the agent.
  • Ingestion points: External snippets, titles, and AI-generated content are ingested via API responses in scripts/baidu_search_manager.py.
  • Boundary markers: Not present; the skill returns raw data without wrapping it in specific security delimiters.
  • Capability inventory: None; the skill is limited to network communication with Baidu and basic console output.
  • Sanitization: The skill truncates input queries to 72 characters but does not sanitize the content returned by the search engine.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 05:18 PM
Security Audit — agent-trust-hub — baidu-search