zai-cli
Warn
Audited by Snyk on Feb 15, 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 skill's "search" and "read" commands perform real-time web searches and fetch arbitrary web pages (e.g., "npx zai-cli search …" and "npx zai-cli read ") and its "repo" command reads GitHub repositories, so the agent ingests untrusted, user-generated third-party content.
Audit Metadata