aws-service-chaos-research

Pass

Audited by Gen Agent Trust Hub on Apr 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill leverages the AWS CLI (aws fis list-actions, aws configure get region) and standard POSIX utilities (jq, awk, tr, date) to dynamically identify available fault injection actions in a specified region and format the output report. This is standard automation behavior for a developer-centric skill.
  • [EXTERNAL_DOWNLOADS]: The agent is instructed to fetch documentation from official Amazon Web Services domains (docs.aws.amazon.com). These downloads are performed using the aws___read_documentation tool to retrieve curated Scenario Library content and architectural guidelines.
  • [SAFE]: Analysis of the skill's instructions, dependencies, and intended workflow reveals no evidence of prompt injection, data exfiltration, or persistence mechanisms. The storage of research reports as local markdown files is a primary and transparent function of the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 24, 2026, 06:16 AM