AI Gateway
v1.0.0Access 340+ AI models through the Agnic AI Gateway. Use when the user wants to chat with an AI model, generate images with AI, list available models, delegat...
⭐ 0· 60·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Benign
medium confidencePurpose & Capability
Name and description (accessing many models via the Agnic Gateway) align with the runtime instructions, which show exact npx agnic commands for listing models, chatting, and generating images. Requiring authentication and a USDC wallet is consistent with a paid gateway service.
Instruction Scope
SKILL.md confines behavior to running specific npx agnic commands and performing input validation before building commands. It does not instruct reading unrelated files, system config, or other credentials. It references an external 'authenticate-wallet' skill for auth steps, which is scope-consistent but assumes that skill exists.
Install Mechanism
There is no install spec in the registry (instruction-only), but the runtime instructions direct the agent to run 'npx agnic@latest ...', which downloads and executes code from the npm registry each time. npm/npx installs are a moderate risk because they execute remote code; the skill itself does not include or pin a package version or checksum.
Credentials
The skill declares no required environment variables or config paths. It does require that the user authenticate a wallet and hold USDC for paid models, which is proportional to a paid gateway. It does not request unrelated credentials or secrets in the SKILL.md.
Persistence & Privilege
always is false and the skill is user-invocable. The skill does not request permanent presence or system-wide changes in its instructions.
Assessment
This skill appears to do what it says: call the Agnic CLI (npx agnic) to talk to many models. Before running it, be aware that 'npx agnic@latest' will fetch and execute code from the npm registry on your machine — only run that if you trust the agnic package and publisher. Consider pinning a specific vetted version instead of @latest or reviewing the package source on npm/GitHub. The skill requires authenticating a wallet and spending USDC for paid models — verify the wallet/auth flow (and the pay.agnic.ai site) are legitimate. Finally, follow the SKILL.md input-validation advice (escape prompts, validate model ids and file paths) to avoid accidental shell injection or leaking secrets in prompts.Like a lobster shell, security has layers — review code before you run it.
latestvk974nz2draan7266j0z1zrcw7184dawr
License
MIT-0
Free to use, modify, and redistribute. No attribution required.