brainstorm

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to use external, public sources (e.g., "Use WebSearch tool" and "docs-seeker skill to read latest documentation of external plugins/packages") as part of its required Research Phase and workflow, so untrusted third-party content could be ingested and influence decisions.