prompt-engineer

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

• Third-party content exposure detected (high risk: 0.90). The skill's prompt-patterns reference (references/prompt-patterns.md) explicitly defines a ReAct pattern with an available tool "search(query): Search the web for information" and examples where the agent executes search actions and uses the resulting observations to drive subsequent Thoughts/Actions/Answers, which clearly ingests open/public (potentially untrusted) web content that can materially influence tool use and decisions.