zenml-quick-wins
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes various ZenML CLI commands (e.g.,
zenml status,zenml stack list,zenml stack describe) to investigate the local environment and stack configuration. It also uses shell commands for environment activation and Git operations. - [EXTERNAL_DOWNLOADS]: The instructions guide the user to install official ZenML integrations and add an MCP server from the official documentation domain (
docs.zenml.io). It also includes a reference to a well-known CDN for loading Chart.js in HTML reports. - [PROMPT_INJECTION]: The skill analyzes the project's codebase for ZenML decorators and patterns. This represents an indirect prompt injection surface where malicious content within the codebase could theoretically influence the agent's analysis, although the skill includes explicit defensive steps such as checking for hardcoded credentials.
- [CREDENTIALS_UNSAFE]: The skill proactively identifies hardcoded credentials in the codebase as a security risk and recommends using ZenML's built-in secrets management tools to handle sensitive information securely.
Audit Metadata