blogwatcher

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

• Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md shows it adds and scans public blogs and RSS/Atom feeds (e.g., "blogwatcher add ... https://example.com" and "blogwatcher scan"), meaning it fetches and reads arbitrary third-party/user-generated web content that can influence its actions and thus could enable indirect prompt injection.