competitor-research

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

• Third-party content exposure detected (high risk: 0.90). The skill's "Competitor Article Fetch Workflow" explicitly instructs the agent to obtain URLs via web search and to "Fetch content: Use mcp_web_fetch or WebSearch to fetch 2–3 top-ranking pages" (i.e., public competitor websites), which the agent is expected to read and use to drive analysis and recommendations—exposing it to untrusted third-party content that could contain indirect prompt injections.