turix-cua
Warn
Audited by Snyk on Mar 3, 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 required workflows explicitly instruct the agent to visit and scrape public websites (e.g., SKILL.md and examples/ai-news-research.md and INDEX.md include web_fetch("https://36kr.com") and steps to open Safari and read articles on 36kr.com, huxiu.com, github.com), so the agent will ingest untrusted, user-generated public web content and use it to decide and drive GUI actions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill's runtime config/default created config points to remote LLM endpoints (https://llm.turixapi.io/v1) which the TuriX agent will call during execution to obtain model outputs that directly drive agent prompts/actions, and the skill depends on those external models as a required runtime dependency.
Audit Metadata