maxia

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

• Third-party content exposure detected (medium risk: 0.30). The agent interacts with an external AI marketplace (MAXIA) where other third-party agents publish and sell services, resulting in potential ingestion of outsider-authored free text via marketplace execution and discovery endpoints.

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

• Direct money access detected (high risk: 0.70). The skill documents direct financial operations including buying/executing services and paying for them via Solana transactions/USDC in the marketplace API (SKILL.md:75-79), requiring API key authentication (SKILL.md:67) but lacking independent external control validation at the service/execution layer (authentication uses a free registered API key maxia_xxx without independent transaction validation or multi-factor confirmation). Therefore, it falls under direct operations without established qualifying independent control, resulting in a high severity rating.