goldrush-cli

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests public, user-generated on-chain and protocol data via streaming commands like goldrush new_pairs and goldrush watch and the "Streaming API" (see SKILL.md and references/overview.md), which the agent is expected to read/process and can materially influence agent decisions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs running "npx @covalenthq/goldrush-cli" which fetches and executes remote code from the npm package (https://www.npmjs.com/package/@covalenthq/goldrush-cli) at runtime — a required dependency that can register as an MCP tool and thus execute remote code and influence agent behavior.