azure-health-bot
Warn
Audited by Snyk on Jun 23, 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). The skill’s runtime workflow fetches Microsoft Learn documentation pages via
mcp_microsoftdocs:microsoft_docs_fetch/WebFetch, which ingests public web content authored by Microsoft (outsider) into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata