zai-orchestrator

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The workflow utilizes web search and zread tools to fetch external data and search results, presenting a low prompt injection risk via active search/fetch.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The installation instructions use npx skills add https://github.com/tianxiao1430-jpg/zai-skills, pointing to an individual-owned GitHub repository without official verification or provenance, presenting a high-tier third-party operational dependency.