writing-staffing

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly instructs spawning researcher agents that perform web search and fetch (resources/researchers.md) and a wiki-editor that has WebSearch/WebFetch access (resources/builders.md), and SKILL.md directs callers to use those research resources—so the agent will fetch and interpret untrusted public web content that can materially influence decisions and actions.