make-dsh-plugin
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of technical documentation and developer recipes for extending the DeepSeek Harness (dsh) platform. It contains no malicious logic or hidden instructions.
- [COMMAND_EXECUTION]: The skill documents standard CLI usage for the dsh platform. These instructions are meant for the user to configure their local development environment and are described in a safe, educational context.
- [EXTERNAL_DOWNLOADS]: The documentation mentions official GitHub repositories and established community project sites. These references are neutral and part of the ecosystem's legitimate tooling landscape.
- [PROMPT_INJECTION]: No attempts to override agent behavior or bypass system constraints were identified in the instructions.
- [DATA_EXFILTRATION]: No sensitive file access or credential harvesting patterns are present. The skill provides proactive advice on secret management (e.g., using .env files).
Audit Metadata