each-sense

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly performs web searches and returns web_search_citations (SKILL.md and references/SSE-EVENTS.md), indicating it fetches and ingests open/public web content (and accepts arbitrary image URLs) which the agent uses to inform responses and actions, exposing it to untrusted third-party content that could contain indirect prompt injections.