tomba

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly includes endpoints that fetch and interpret public/untrusted web content (e.g., Author Finder and LinkedIn Finder which take arbitrary article or profile URLs, Domain Search and Email Sources that return emails found "on the internet"), so third‑party page content could be read and materially influence the agent's outputs and follow‑up actions.