digital-health-clinical-asr-build
Warn
Audited by Snyk on Jun 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). At runtime, Step 2c performs Merriam-Webster lookups by sending each term to the external
dictionaryapi.com/merriam-webster.comservice (Path A/B), and the fetched respelling text is then converted to IPA and inserted into the agent’s LLM context via the manifest-building conversation flow.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata