agent-creator

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs agents to use external MCP tools (e.g., mcp__exa__web_search_exa and mcp__context7__query-docs / Context7/Exa) to fetch and verify public documentation and web search results, which the agent is expected to read as part of its workflow, exposing it to untrusted third‑party content.