ml-pipeline-creation
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of high-level documentation and architectural guidance. It does not include any executable scripts, shell commands, or configuration files that could be run by an agent.
- [SAFE]: The instructions promote secure development practices, specifically advising the agent to avoid moving production data without authorization, to use pinned dependencies for reproducibility, and to require explicit human approval before deploying models or altering infrastructure.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that involves reading existing preprocessing and training code. While this identifies a potential ingestion surface for untrusted content, the skill provides specific safety boundaries directing the agent to flag security and regulatory requirements rather than executing untrusted code blindly.
Audit Metadata