orchestration

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

• Third-party content exposure detected (high risk: 0.70). This skill explicitly grants worker agents permission to use WebFetch/WebSearch (see "Execution tools you DELEGATE to agents: Write Edit Bash WebFetch WebSearch LSP"), which lets them fetch and ingest arbitrary public web content that is untrusted/user-generated and that the agents are expected to read/interpret as part of their workflows.