team-create-plan

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

• Third-party content exposure detected (high risk: 0.90). The skill's Researcher role explicitly requires "STEP 2
• WEB RESEARCH: Search for best practices... Find similar implementations..." which directs agents to fetch and interpret public web content (blogs, docs, examples) and use those findings to validate claims and alter design decisions, exposing the agent to untrusted third-party content.