opensea
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [PROMPT_INJECTION]: Identifies an indirect prompt injection surface where malicious instructions could be embedded in metadata retrieved from the OpenSea API. 1. Ingestion points: NFT metadata and collection descriptions fetched via scripts such as
opensea-nft.shandopensea-collection.sh. 2. Boundary markers: The scripts do not implement delimiters or 'ignore instructions' warnings when presenting retrieved data to the agent. 3. Capability inventory: The skill has the capability to fulfill marketplace orders and execute token swaps viaopensea-swap.sh. 4. Sanitization: No sanitization or validation of the retrieved text is performed before it is added to the agent context. - [EXTERNAL_DOWNLOADS]: Recommends the installation of the
@opensea/clipackage from the official NPM registry, which is a verified resource provided by the vendor. - [COMMAND_EXECUTION]: Uses
curlfor REST API interactions andnodewith theviemlibrary to facilitate on-chain transaction execution, which is standard for blockchain-integrated tools. - [DATA_EXFILTRATION]: Performs network operations targeting official vendor domains including
api.opensea.ioandstream.openseabeta.com. Theopensea-stream-collection.shscript passes the API key as a URL parameter for WebSocket authentication, which is the documented protocol for the OpenSea Stream API.
Audit Metadata