ml-pipeline-creation

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill is designed to execute arbitrary local Python scripts as defined in a configuration file (e.g., pipeline.yaml). This permits the agent to run code on the host system to perform tasks such as data processing and model training.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) because it processes configuration files and scripts from potentially untrusted project directories.
  • Ingestion points: Pipeline definition files (YAML/JSON) and component scripts (e.g., preprocess.py).
  • Boundary markers: The skill instructions do not define specific delimiters or warnings to isolate or ignore embedded instructions in the ingested data.
  • Capability inventory: The skill utilizes the agent's ability to execute shell commands and Python scripts to run pipeline stages.
  • Sanitization: No sanitization or validation of the script content or configuration parameters is described.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 09:01 PM
Security Audit — agent-trust-hub — ml-pipeline-creation