research-strategy-web

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly directs use of the "assist/research/web-research" subagent to retrieve current API/library documentation, code examples, tutorials and production examples from the open web (public websites and tutorials), meaning the agent will fetch and interpret untrusted third-party content as part of its workflow.