tokenomist

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

• Third-party content exposure detected (high risk: 0.80). The skill makes live requests to the external Tokenomist API (BASE_URL https://api.tokenomist.ai) via TokenomistClient._request (tools/client.py using core.http_client.proxied_get) and SKILL.md/tool wrappers require ingesting those API responses (token list, allocations, emissions, unlock events) which the agent reads and uses to drive resolution and subsequent tool calls, so untrusted third‑party content can materially influence agent behavior.