cordis-plugin-development
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides a structured and legitimate development workflow for extending the Harness platform using specialized tools like
plugin_managerandcordis_inspect_query. - [SAFE]: Security-conscious instructions are included, such as explicitly advising the agent against searching for authentication tokens, hardcoding credentials, or performing unauthorized environment modifications. It specifically recommends using the
!!jsYAML tag as a secure way to reference existing system credentials instead of exposing secrets in text. - [SAFE]: The skill promotes the principle of least privilege by instructing the agent to minimize tool calls, avoid manual file writes outside of the workspace, and restore any user settings changed during testing.
- [SAFE]: No patterns of obfuscation, malicious data exfiltration, unauthorized remote code execution, or prompt injection were detected in the instructions, references, or templates.
Audit Metadata