Skills
skills/bighardperson/computer-science-skills-collection/baidu-search/Gen Agent Trust Hub

baidu-search

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill connects to qianfan.baidubce.com to retrieve search results. This target is the official API endpoint for Baidu's AI Search service, which is a well-known technology provider.
  • [DATA_EXFILTRATION]: The script scripts/search.py transmits search queries and an authorization token to Baidu's infrastructure. This is a primary functional requirement of the skill and targets a well-known service domain.
  • [SAFE]: Authentication is handled via the BAIDU_API_KEY environment variable. The skill provides documentation in references/apikey-fetch.md for proper configuration, adhering to safe credential management practices.
  • [SAFE]: The skill processes external search data from the Baidu API.
  • Ingestion points: API response data in scripts/search.py.
  • Boundary markers: The output is formatted as structured JSON to provide separation between data and instructions.
  • Capability inventory: Network operations via requests.post to a well-known service.
  • Sanitization: Results are parsed, filtered for specific keys, and serialized as JSON before being returned to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 01:02 AM
Security Audit — agent-trust-hub — baidu-search