nw-operational-safety

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly uses WebSearch/WebFetch to retrieve content from identified URLs and instructs the agent to scan, extract, and act on fetched web content (under "Web Tools (WebSearch, WebFetch)" and "Adversarial Output Validation"), which means untrusted public web pages can be read and materially influence tool decisions.