deepseek
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides documentation for using the DeepSeek AI CLI tool, including model selection and account management. The instructions are transparent and consistent with the stated purpose of the skill.
- [DATA_EXPOSURE]: The skill provides guidance on how to initialize API keys using
initor--cfg apikey=<key>. This is a standard practice for local tool configuration and does not involve hardcoded credentials or unauthorized data exfiltration. - [INDIRECT_PROMPT_INJECTION]: The skill acts as an interface for an external LLM (DeepSeek). While any system processing external model output has a theoretical surface for indirect prompt injection, this skill does not implement unsafe data interpolation or automated actions that would escalate this risk.
Audit Metadata