autoboy

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill requires constructing authenticated API requests with a user's API key in an Authorization: Bearer header, which forces the agent to handle (and potentially emit) secret values verbatim.

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

• Third-party content exposure detected (medium risk: 0.65). Required runtime workflow includes calling AutoBoy REST endpoints (e.g., GET /projects, GET /projects/{slug}, GET /projects/{slug}/buyers, GET /orders) whose responses are explicitly “third-party content” and therefore can contain outsider-authored free text that the agent may ingest into LLM context.

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

• Direct money access detected (high risk: 1.00). The skill explicitly provides a REST API for placing buy orders and "auto-buys the token within moments of launch" (market/crypto order execution). It documents endpoints for buyers/projects, API key requests, and handles USDC amounts and withdrawal formats — i.e., concrete crypto/market order and token-launch operations that can move funds. This meets the definition of Direct Financial Execution.