azure-ai-vision-imageanalysis-java

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

• Third-party content exposure detected (high risk: 0.90). The skill's examples and workflow (e.g., multiple analyzeFromUrl calls in SKILL.md and references/examples.md, including the "Complete Application Example" that calls a raw.githubusercontent URL) show the agent fetching and analyzing arbitrary external image URLs, which are untrusted third‑party content whose extracted captions/text could materially influence downstream actions.