neon-ai-gateway@r2
CAUTION· install onlyPublisher claims: "One API and one credential for frontier and open-source LLMs and embedding models, built into your Neon branch and powered by Databricks. Use when a user wants to call an LLM, generate embeddings, add AI/chat/an agent to their app, route between model providers (OpenAI, Anthropic, Google/Gemini, Meta, Alibaba, and more), or avoid juggling separate provider API keys and accounts — especially when they already use Neon and want AI requests to branch with their project. Works with the OpenAI SDK, Anthropic SDK, google-genai, the Vercel AI SDK, and Mastra by changing only the base URL. Triggers include "call an LLM", "add AI to my app", "chat completion", "model routing", "LLM proxy/gateway", "one API for all models", "use Claude/GPT/Gemini", "AI SDK", "Mastra agent", "Neon AI Gateway", "generate embeddings", "generate images", and "log/rate-limit AI calls"." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
Is neon-ai-gateway@r2 safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-07 and scored it 69/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: HTML comment carrying imperative instructions to the agent; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
prettier-ignoreFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.- **Provision via `neon.ts` (recommended).** Enable `aiGateway` in `neon.ts` and run `neon deploy` (or `neon config apply`). Provisioning, `neon link`, and `neon checkout` pull `NEON_AI_GATEWAY_TOKEN`Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- **Pull into the environment via CLI.** `neon env pull` writes the two vars to `.env`/`.env.local`, or `neon-env run -- <cmd>` injects them at runtime without a file — but only when `neon.ts` declareFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.The gateway is **branch-scoped**: each branch gets its own gateway host. When a `neon.ts` is present, `neon checkout` applies the policy as it _creates_ a branch, so a fresh preview/CI branch comes upFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- **Older CLI.** `neon` 8.23.3 and earlier refuse `aiGateway` on a Free plan with "isn't available on the Free plan". Update with `npm i -g neon@latest` (8.23.4 or later) and re-run.Fix: Pin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.When `aiGateway` is enabled, Neon injects the gateway credentials as **Neon-branded** env vars. Inside a deployed Neon Function these are injected automatically; locally, `neon env pull` writes them tFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.
What would make this Verified
11 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
- Unclaimed publisher≈ +8 on the totalClaim neondatabase: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Unpinned dependencies≈ +1 on the totalPin exact versions (and ideally hashes) in package.json, requirements or the install script so the bundle cannot change under you.
- Unpinned dependency≈ +1 on the totalPin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.