skill-architect

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

• Third-party content exposure detected (high risk: 0.90). The skill's references and subagent templates (e.g., references/self-contained-tools.md and references/subagent-template.md / agents/research-workflow.md) explicitly require tools like WebSearch and WebFetch and instruct agents to execute searches, read and extract content from public web pages, so the agent will ingest untrusted third‑party web content as part of its workflow.