gmgn-dev-score

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

• Third-party content exposure detected (medium risk: 0.30). The workflow queries user-created token metadata, portfolio activity feeds, and token creation parameters from the Gmgn API via gmgn-cli (such as token symbols, names, and transfer records), which can contain outsider-authored text and token details.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs fetching an IPv6 check URL (https://ipv6.icanhazip.com) during runtime troubleshooting, constituting an unverifiable external runtime dependency with unknown provenance.