duoduo-pipeline
Warn
Audited by Snyk on Oct 30, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The required workflow uses a mechanical layer script to fetch external feeds and push them via duoduo session notify into the LLM brain job, allowing outsiders to submit untrusted text into monitored inputs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata