researching-web

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly directs the agent to "Search the web using Perplexity AI" via the mcp__perplexity-ask__perplexity_ask tool, which ingests open/public web content (untrusted user-generated sources) that the agent is expected to read and use to drive research and answers, creating a clear avenue for indirect prompt injection.