xfyun-search

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill functions as a standard search utility, interacting only with the official iFlytek API endpoints.
  • [DATA_EXPOSURE]: Credential management follows best practices by instructing the user to use environment variables (XFYUN_API_PASSWORD) rather than hardcoding secrets.
  • [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection common to all search tools.
  • Ingestion points: Search result titles, summaries, and full text retrieved in scripts/search.py.
  • Boundary markers: None explicitly implemented in the formatting logic.
  • Capability inventory: Execution of the scripts/search.py script via the agent's shell capability.
  • Sanitization: No explicit sanitization or filtering of the external search content is performed before outputting it to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 10:01 PM
Security Audit — agent-trust-hub — xfyun-search