strands
Warn
Audited by Snyk on Nov 4, 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 skill instructs the agent to build and integrate Strands agents into web frameworks (Fastapi, Express, Next.js) where HTTP request bodies containing user prompts are processed and passed to the agent, exposing the runtime workflow to outsider-authored free text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata