dsh-plugin-dev
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructional content and local utility scripts for software development. No malicious behavior or security vulnerabilities were identified.
- [COMMAND_EXECUTION]: The included scripts
lint.mjsandtest-lint.mjsutilizenode:child_processto execute localgitandnodecommands. These are used for project-specific tasks such as checking the DeepSeek Harness version, verifying repository commits, and running self-tests against local code fixtures. The execution is confined to the local environment and user-specified directories. - [PROMPT_INJECTION]: The instructions consist of technical guidelines and best practices for DSH plugin development. There are no attempts to override agent safety protocols, extract system prompts, or bypass content filters.
- [DATA_EXFILTRATION]: No network exfiltration patterns, hardcoded credentials, or unauthorized access to sensitive files (such as SSH keys or environment secrets) were found.
Audit Metadata