azure-ai-contentsafety-java

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

• Third-party content exposure detected (high risk: 0.80). The skill's documentation and core examples (SKILL.md and references/examples.md) explicitly show ingesting external content via ContentSafetyImageData.setBlobUrl("https://...") and analyzeText() on arbitrary text, meaning the agent can fetch and analyze untrusted/public URLs or user-provided text which directly influence moderation decisions and subsequent actions.