brainstorm

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

• Third-party content exposure detected (high risk: 0.70). The skill's SKILL.md explicitly instructs the agent to use WebSearch in Prompt Mode (Phase 4: "Reference (optional)") to fetch external web references and incorporate them into the improved prompt, which exposes the agent to untrusted public web content that could influence its outputs.