opensea-api
Query OpenSea marketplace data via the official CLI, SDK, MCP server, or shell scripts. Get floor prices, collection stats, NFT details, token data, trending collections, drops, events, search, favorites, profile and collection settings, and other wallet-scoped operations. For trading use opensea-marketplace, for token swaps use opensea-swaps.
72
78%
Does it follow best practices?
Impact
55%
2.20xAverage score across 2 eval scenarios
Medium
Suggest reviewing before use
Fix and improve this skill with Tessl
tessl review fix ./opensea-api/SKILL.mdW009: Direct money access capability detected (payment gateways, crypto, banking).
What this means
The skill is specifically designed for direct financial operations, giving the agent the ability to move money or execute financial transactions — such as payment processing, cryptocurrency operations, banking integrations, or market order execution.
Why it was flagged
The skill exposes explicit crypto/blockchain capabilities: it includes wallet-authenticated scopes, accepts an EVM private key for headless SIWE, and provides commands/MCP tools and scripts that build transactions for minting, cross-chain mints, contract deployment, and asset transfers (transaction data intended to be signed and submitted). These are specific blockchain/financial operation primitives (wallets/signing/transactions), so the skill grants direct financial execution capability (crypto-related).
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
In this skill, required runtime reads OpenSea API JSON (including user-generated NFT/collection metadata and descriptions) via scripts like `scripts/opensea-get.sh` → `emit_response` → `_response-markers.sh`, meaning attacker-authored content from the OpenSea ecosystem is ingested into the agent’s prompt context when the workflow uses API outputs.
- Repository
- ProjectOpenSea/opensea-skill
- Commit
70c513e
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.