azure-ai-contentsafety-py

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.70). The required runtime workflow calls client.analyze_text(request) with AnalyzeTextOptions(text=...), so any free-form text supplied by an outsider (e.g., user comments/messages) would be ingested into the LLM context via the SDK’s request payload; the SKILL.md itself doesn’t constrain the source of that text.