skill-editor

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow and quality gates call for an "external research" agent and include an external-research-template that instructs searching and ingesting community forums, blog posts and URLs (see Quality Gate 2 / "External research findings documented" and references/external-research-template.md), meaning the agent will fetch and interpret untrusted public web content that can influence planning and actions.