nemoclaw-user-guide

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

• Third-party content exposure detected (high risk: 0.85). The required workflow fetches canonical NemoClaw Markdown from a public docs site at runtime (e.g., https://docs.nvidia.com/nemoclaw/llms.txt and specific .md pages, or via the MCP server https://docs.nvidia.com/nemoclaw/_mcp/server), which is outsider-authored free text that the agent ingests into the LLM context.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly requires the agent at runtime to fetch and use external Markdown docs from https://docs.nvidia.com/nemoclaw/_mcp/server and https://docs.nvidia.com/nemoclaw/llms.txt (and the linked .md pages under https://docs.nvidia.com/nemoclaw/...) which are retrieved and injected into the agent's context to control prompts/responses, so these URLs are runtime dependencies that directly influence the agent's instructions.