glm-web-search
Fail
Audited by Snyk on Feb 28, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). This prompt instructs the agent/user to read or request an API key and embed it verbatim into commands, files and URLs (e.g., writing the API key into glm.json and replacing "your-key" in the mcporter URL), which requires exposing secrets in outputs.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). SKILL.md step 6 documents calling the glm-search MCP's webSearchPrime search tool (via https://open.bigmodel.cn) which returns webpage titles, URLs and summaries from public websites—the agent ingests and acts on this untrusted third‑party web content.
Audit Metadata