experts

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

• Third-party content exposure detected (high risk: 0.90). The Agent Prompt Template explicitly tells reviewer agents to "use [browser MCP] to inspect the running site at [URL]" (SKILL.md Agent Prompt Template / Workflow), meaning the skill fetches and interprets arbitrary public URLs provided by users, exposing the agent to untrusted third-party content that can influence decisions.