docker-and-kubernetes-pro

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill defines a maintenance workflow in modules/research-checklist.md that encourages the agent to fetch and process data from external sources including Wikipedia and the kubernetes/website GitHub repository.
  • Ingestion points: The modules/research-checklist.md file contains instructions for the agent to utilize tools (documented as adn_skills) to retrieve content from Wikipedia and the official Kubernetes documentation repository on GitHub.
  • Boundary markers: Absent. The instructions do not specify the use of delimiters or warnings to the agent to ignore potentially malicious instructions embedded in the external content.
  • Capability inventory: The skill is designed to assist users in creating Kubernetes manifests, defining GitOps pipelines, and setting up security policies. If the agent's logic is influenced by external content, it could generate insecure configurations.
  • Sanitization: Absent. The workflow relies on the agent to "cross-check" data manually without automated validation or sanitization of the retrieved text strings.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 05:38 PM
Security Audit — agent-trust-hub — docker-and-kubernetes-pro