coingecko

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to ask for, retrieve from memory, and use a user's CoinGecko API key (CG-…) and to build/execute API calls (including using curl/bash_tool), which implies embedding the secret verbatim into generated requests/commands and thus risks secret exfiltration.

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly requires making live requests to public CoinGecko and GeckoTerminal APIs (see SKILL.md and references/* files such as references/core.md and references/onchain-networks.md), and it consumes unreviewed/on-chain and user-contributed data (GeckoTerminal lists tokens automatically and coin descriptions/links are returned) which the agent is required to read and use to drive decisions (prices, trading, dashboards), so untrusted third‑party content can materially influence tool use.