chaos-engineering

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides numerous shell command examples for infrastructure fault injection and system manipulation.
  • Evidence: Instructions for using tc (traffic control) with sudo, iptables for network blocking, and kubectl for resource management are provided in SKILL.md and references/experiment-catalog.md.
  • [COMMAND_EXECUTION]: The skill directs the agent to inspect the local file system to identify installed components.
  • Evidence: A "Companion check" in SKILL.md instructs the agent to run ls on various local paths (e.g., ~/.claude/skills/) to check for recommended companion skills.
  • [EXTERNAL_DOWNLOADS]: The skill references and suggests downloading configuration from external repositories.
  • Evidence: The experiment catalog in references/experiment-catalog.md provides instructions to apply Kubernetes manifests directly from hub.litmuschaos.io.
  • Evidence: README.md and SKILL.md provide commands to install additional skills from the AbsolutelySkilled repository using npx.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 03:03 PM
Security Audit — agent-trust-hub — chaos-engineering