opensea-research

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The required workflow queries OpenSea marketplace and NFT collection data via the Crawlora API, which returns community-generated descriptions, metadata, and listings containing outsider-authored free text.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill queries the Crawlora API at https://api.crawlora.net/api/v1 via a local helper script, which constitutes a runtime operational dependency on a third-party service provider.