ask-glm
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: 0.75). This skill’s required workflow includes “Grounded web research” via
zai websearch "<query>"(public web content fetched at runtime and treated as untrusted data), which can introduce outsider-authored free text into the agent/LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata