open-agent-sdk

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

• Third-party content exposure detected (high risk: 0.90). The skill's Built-in Tools Reference includes "WebFetch" and "WebSearch" (and examples/defaults that allow all built-in tools), which let the agent fetch and parse public web pages and search results — untrusted, user-generated third‑party content that the agent is expected to read and could materially influence its actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The MCP server example config runs npx to fetch and execute remote packages at runtime (e.g., npx -y @modelcontextprotocol/server-filesystem and npx @playwright/mcp@latest — https://www.npmjs.com/package/@modelcontextprotocol/server-filesystem, https://www.npmjs.com/package/@playwright/mcp), which downloads and runs remote code and therefore can directly execute code during skill runtime.