Nvidia Model Config
v1.0.5Add the NVIDIA provider to OpenClaw with SecretRef apiKey (no plaintext in openclaw.json). Documents shell vs systemd gateway env so the key actually resolve...
⭐ 0· 80·0 current·0 all-time
byWei Li@0xli
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the included script and models. The script inserts a providers.nvidia block, uses a SecretRef-style env id, and includes the listed model entries and NVIDIA API endpoint — all directly relevant to the stated purpose.
Instruction Scope
Instructions and the script operate only on the target openclaw.json, optional env file (e.g., ~/.config/openclaw/gateway.env), and a user systemd override directory — all in-scope. Caution: using --inline-key or running with --dry-run while using inline-key will print plaintext keys to stdout; the SKILL.md warns about inline-key but does not call out the dry-run printing risk explicitly.
Install Mechanism
No install spec; this is an instruction-only skill with a small local Python script. Nothing is downloaded or written outside user-controlled files and typical user config locations.
Credentials
The skill requests no platform credentials and does not declare required env vars. It optionally writes a local env file and a user systemd override to expose NVIDIA_API_KEY to the OpenClaw gateway — appropriate for the task. Users should avoid --inline-key for long-lived/shared configs and be mindful that dry-run will display inline keys if used.
Persistence & Privilege
always:false and no autonomous invocation settings are unusual. The script may create a user-level systemd override for openclaw-gateway (user scope) and writes a per-user env file; this is expected for configuring a gateway service and does not modify other skills or system-wide configuration.
Assessment
This skill appears coherent and implements exactly what it claims, but review and follow these safety steps before use:
- Prefer the secure default (SecretRef) over --inline-key. Only use --inline-key for short-lived local tests and never commit configs with inline keys.
- Beware: running --dry-run while using --inline-key will print the config (and the inline key) to stdout. Avoid dry-run when testing inline keys or ensure your terminal/stdout is not being captured.
- If you use --setup-env the script will write an env file (mode 600) to the path you supply; confirm the path and permissions. The script sets 0600 which is good practice.
- The script will create a user systemd override in ~/.config/systemd/user/... for the openclaw-gateway service. Verify the correct service name and that you want to reload/restart that user service.
- Back up your openclaw.json (use --backup or manual copy) before running in non-dry-run mode.
- Inspect the script yourself (it is included) and run it locally — it performs only local file edits and writes; it contains no network-exfiltration code. If you run it on a machine with remote logging/monitoring, be mindful of where stdout/stderr may be captured.
If you want additional assurance, request a short code review of scripts/merge_nvidia_config.py for your environment or run it in a sandboxed/test workspace first.Like a lobster shell, security has layers — review code before you run it.
latestvk97f9w1e1664sef0symhbg5f5s84acxs
License
MIT-0
Free to use, modify, and redistribute. No attribution required.