workflow
Warn
Audited by Snyk on Aug 26, 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 only outsider free text shown in the required runtime path is userMessage passed into
DurableAgent.stream({ messages: [{ role: "user", content: userMessage }] }), i.e., a direct handoff of caller-authored text into the LLM.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata