skopos

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

• Third-party content exposure detected (medium risk: 0.30). Runtime path: the required workflow “free chat API” sends user/agent-provided message text to https://www.tryskopos.xyz/api/chat, meaning outsider-authored free text is ingested by the service/LLM before producing text.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill demonstrably fetches https://www.tryskopos.xyz/llms.txt (demo curl) and https://www.tryskopos.xyz/openapi.json (discovery) at runtime, and those agent-readable files/schemas can directly control agent prompts/instructions, so they are flagged.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (high risk: 1.00). The SKILL explicitly exposes crypto payment/trading endpoints and an x402 inline payment flow: paid API endpoints (quote, flash-order) for swaps/bridges and advanced orders, plus instructions that an agent's wallet can pay inline via the x402 challenge and pinned payment fields (including payTo address and amount limits). These are specific crypto/financial APIs designed to initiate payments and market orders (even if final signing happens in a wallet), so it grants direct financial execution capability.