zai-web-research
Warn
Audited by Snyk on Jul 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The required workflow explicitly instructs runtime use of
zai read <best-url>/web_readerto fetch arbitrary web page text at the provided URL, which is outsider-authored free-form content that the LLM then ingests as “clean text”.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata