workmanager

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

• Third-party content exposure detected (high risk: 0.80). The skill's workflow (e.g., DownloadWorker in SKILL.md and references/chaining.md) reads and processes arbitrary URLs from inputData (examples include "https://example.com/file.zip" and "https://example.com/data.json"), so untrusted third-party content is fetched and can influence chaining/branching and subsequent work decisions.