machine-learning-ops-ml-pipeline

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill implements a multi-agent workflow where user-supplied content from the $ARGUMENTS variable is directly embedded into the prompts of several sub-agents.
  • Ingestion points: The $ARGUMENTS placeholder is used in the prompt field of <Task> blocks for data-engineer, data-scientist, and ml-engineer sub-agents in SKILL.md.
  • Boundary markers: There are no delimiters (such as XML tags or Markdown code blocks) or instructions telling the sub-agents to treat the $ARGUMENTS content as untrusted data or to ignore embedded instructions.
  • Capability inventory: The sub-agents are tasked with generating high-impact outputs, including production Python code, Kubernetes manifests, CI/CD pipeline configurations (GitHub Actions/GitLab CI), and Infrastructure as Code (Terraform).
  • Sanitization: The skill does not perform any validation, filtering, or escaping of the user input before passing it to the sub-agents, creating a surface for indirect prompt injection where an attacker could provide input that misdirects the sub-agents to generate malicious infrastructure or backdoored code.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 03:47 PM