verify

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

• Third-party content exposure detected (high risk: 0.90). The skill's Workflow step 2 explicitly instructs the agent to perform WebSearch of open/public sources (e.g., Wikipedia, Google Scholar, JSTOR, publisher and encyclopedia websites) and step 3 requires the agent to read and act on those results to produce verdicts and optionally edit notes, meaning untrusted third‑party content could materially influence behavior.