laniameda-instagram-carousel-extract

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and browses Instagram carousel posts (Step 2: "Go to [URL]" using browser-use-cloud to visually read slides) and then interprets and acts on that untrusted, user-generated content (transcribing, classifying, and saving prompts/workflows), so third-party content can materially influence agent behavior.