skills/vm0-ai/vm0-skills/deepseek/Gen Agent Trust Hub

deepseek

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes examples using curl and jq to interact with the DeepSeek API. These commands are used for legitimate API requests and data parsing.
  • [EXTERNAL_DOWNLOADS]: The skill makes network requests to api.deepseek.com, which is the official endpoint for the DeepSeek AI service. This is the primary intended function of the skill.
  • [CREDENTIALS_UNSAFE]: The skill correctly instructs the user to manage their API key via an environment variable (DEEPSEEK_API_KEY) and references it in the vm0_secrets metadata, following safe practice for secret handling.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 05:19 AM