domain-research

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

• Third-party content exposure detected (high risk: 0.90). The skill's Phase 1 research agents (Agent 1 and Agent 4 in the mandatory DISCOVER phase) and the Source Hierarchy explicitly call for web search and fetching "official documentation" and "web search" results (see Phase 1 agent methods and the "Research follows a strict source hierarchy" section), which the agents must read and use to drive classifications and chain-composition decisions, exposing the agent to untrusted public web content that can influence behavior.