api-provider-setup

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs adding API keys directly into config files and includes examples and curl commands that require embedding API keys/tokens verbatim, so an agent performing it would need to handle and output secrets directly.

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs adding external model API providers (baseUrl/apiKey examples such as "anapi", "zai", "openrouter-vip" in the "常见中转站配置示例" and the configuration/templates sections), meaning the agent will call and ingest responses from third‑party model endpoints whose outputs could contain instructions that influence agent behavior.