xfyun-search
Warn
Audited by Snyk on Jul 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The required workflow calls a public web search API that returns outsider-authored page titles/summaries and (optionally) full page text, which the script prints/returns as readable text (and thus can be fed into the agent/LLM context), e.g.,
scripts/search.pyreadsresp.read()and outputsdata.search_results.documents[].contentwhen--no-fulltextis not set.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata