Atlas / Skills / bankrbot / Opensea

OpenseaSAFE

skills/bankrbot/opensea

Bankr Skills equip builders with plug-and-play tools to build more powerful agents.

Verdict
SAFE
Grade
B
Trust score
89 /100
Version
1.0
Hosts
1 documented
License
—
Stars
1,202
01

Overview

Bankr Skills equip builders with plug-and-play tools to build more powerful agents.

Read from source at commit 4029e336cef5OBSERVED · 2026-10-09
02

Install

Commands as the repository documents them. They are shown, not run.

npm install -g @opensea/cli
npm install -g @opensea/cli
03

Host compatibility

What the documentation claims. We have not run a compatibility test.

HostStatusNotes
cursormentioned
04

What it tells the agent

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: opensea
description: Query NFT and token data, trade NFTs on Seaport, swap ERC20 tokens via DEX aggregator, configure wallet signing providers, and build/register/gate AI agent tools on Base. Covers the full OpenSea developer surface across CLI, MCP server, shell scripts, and SDK. Pick the right sub-skill using the routing table below, then read that sub-skill's SKILL.md for operational detail.
license: MIT
compatibility: Requires network access and Node.js >= 18. Set $OPENSEA_API_KEY (free instant key at https://docs.opensea.io/reference/api-keys#instant-api-key-for-agents) for all read/write operations. Write operations (marketplace, swaps) additionally require a wallet provider — Bankr, Privy, Turnkey, Fireblocks, or a local PRIVATE_KEY — configured per opensea-wallet/SKILL.md. `curl` and `jq` recommended for shell-script flows.
metadata:
  author: ProjectOpenSea
  version: "1.0"
---

# OpenSea (router)

Entry point for OpenSea agent skills. Pick the sub-skill based on task, then read its `SKILL.md`:

| Task | Sub-skill |
|---|---|
| Query NFT/token data, search, drops, events | [`opensea-api/SKILL.md`](opensea-api/SKILL.md) |
| Buy/sell NFTs on Seaport, sweeps, cross-chain | [`opensea-marketplace/SKILL.md`](opensea-marketplace/SKILL.md) |
| Swap ERC20 tokens via DEX aggregator | [`opensea-swaps/SKILL.md`](opensea-swaps/SKILL.md) |
| Configure wallet signing (Privy/Turnkey/Fireblocks/Bankr) | [`opensea-wallet/SKILL.md`](opensea-wallet/SKILL.md) |
| Build/register/gate AI agent tools (ERC-8257) | [`opensea-tool-sdk/SKILL.md`](opensea-tool-sdk/SKILL.md) |

Always read the sub-skill `SKILL.md` before executing. This router intentionally has no operational detail.

## Quick decision guide

- **Read-only queries** (collections, NFTs, tokens, search, stats, events, drops): `opensea-api`
- **Write operations** (buy, sell, make offers, fulfill listings): `opensea-marketplace`
- **Token swaps** (ERC20 to ERC20, cross-chain): `opensea-swaps`
- **Wallet setup** (before any write operation): `opensea-wallet`
- **Tool building** (register, gate, monetize AI tools): `opensea-tool-sdk`

## Source

Maintained at [github.com/ProjectOpenSea/opensea-skill](https://github.com/ProjectOpenSea/opensea-skill). File issues and contributions there.
05

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
declared (6 observation(s))
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (1)

LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
opensea-wallet/references/wallet-setup.md:296
export RPC_URL="http://127.0.0.1:8545"  # local dev node only (Hardhat/Anvil/Ganache)

Gates applied: no_behavioural_pass.

Audited 2026-10-09 · audit v0.4.1 · source sha 4029e336cef5full audit observations/trust-audit/skill/bankrbot__opensea.json · Report an issue / request a re-scan
06

Audit history

Every audit this skill has had.

DateSourceVerdictGradeScoreChange
2026-10-094029e336cef5SAFEB89first audit
07

Questions

What does the Opensea skill do?

Bankr Skills equip builders with plug-and-play tools to build more powerful agents.

Is Opensea safe to install?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.

What can Opensea access on my machine?

The audit observed that it reaches the network. Each of those is consistent with what it says it does. Secrets in the source: none found.

Which assistants does Opensea work with?

Its documentation mentions cursor. That is what the text claims, not a compatibility test we ran.

How current is this page?

The grade is for one exact copy of the source (4029e336cef5), read on 2026-10-09. The repository is watched, and a new audit runs when it changes — this is the first audit.

Advertisement