nemoclaw-user-configure-inference
Connects NemoClaw to local inference servers for seamless integration with models like Ollama and vLLM, enhancing AI capabilities.
Install this skill
or
86/100
Security score
The nemoclaw-user-configure-inference skill was audited on May 31, 2026 and we found 6 security issues across 2 threat categories. Review the findings below before installing.
Categories Tested
Security Issues
medium line 91
Access to hidden dotfiles in home directory
SourceSKILL.md
| 91 | `~/.nemoclaw/ollama-proxy-token` with `0600` permissions. |
medium line 259
Access to hidden dotfiles in home directory
SourceSKILL.md
| 259 | NemoClaw pulls the vLLM image, downloads model weights into `~/.cache/huggingface`, starts the `nemoclaw-vllm` container on `localhost:8000`, and prints progress markers while the model loads. |
low line 170
External URL reference
SourceSKILL.md
| 170 | Enter the base URL of your local server, for example `http://localhost:8000/v1`. |
low line 187
External URL reference
SourceSKILL.md
| 187 | NEMOCLAW_ENDPOINT_URL=http://localhost:8000/v1 \ |
low line 239
External URL reference
SourceSKILL.md
| 239 | NEMOCLAW_ENDPOINT_URL=http://localhost:8080 \ |
low line 339
External URL reference
SourceSKILL.md
| 339 | If Docker is not already logged in to `nvcr.io`, onboard prompts for an [NGC API key](https://org.ngc.nvidia.com/setup/api-key) and runs `docker login nvcr.io` over `--password-stdin` so the key is ne |
Scanned on May 31, 2026
View Security Dashboard