research-workflow

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly instructs in Step 2 and Step 3 to use rebyteai/internet-search and rebyteai/deep-research to fetch and synthesize information from 10+ public web/news/other sources, so the agent ingests untrusted third-party content that can influence its analysis and actions.