gmgn-track

Warn

Audited by Snyk on Nov 14, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (medium risk: 0.30). The required workflow runs track kol, track smartmoney, and track follow-wallet and presents the returned trade feed, which includes outsider-controlled free text such as token base_token.symbol (anyone can name a newly launched token), and wallet maker_info.name, twitter_username, and twitter_name (set by wallet owners), all read without the agent selecting a specific item.

MEDIUM W013: Attempt to modify system services in skill instructions.

  • Attempt to modify system services in skill instructions detected (medium risk: 0.40). The skill is mostly read-only data querying, but it tells the agent to run gmgn-cli config --apply <KEY> (writing credentials to a config file) and to direct the user to disable IPv6 on their network interface, which changes machine network state.

Issues (2)

W011
MEDIUM

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

W013
MEDIUM

Attempt to modify system services in skill instructions.

Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 14, 2026, 02:47 AM
Issues
2