zai-cli

Warn

Audited by Snyk on Mar 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 SKILL.md and references/examples.md explicitly state the CLI performs real-time web search and "web page to markdown extraction" (e.g., "read this page", "Convert Web Page to Markdown"), meaning the agent fetches and interprets arbitrary public web/GitHub content that could inject instructions into its workflow.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 24, 2026, 03:46 PM
Issues
1