ecs-operation-review

Pass

Audited by Gen Agent Trust Hub on Jul 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a well-designed operational assessment tool for Amazon ECS. It enforces a read-only access model and relies on standard AWS CLI commands to retrieve configuration data, explicitly forbidding mutation operations such as create, update, or delete.
  • [COMMAND_EXECUTION]: The skill executes multiple AWS CLI read-only commands (e.g., aws ecs describe-services, aws ec2 describe-subnets) to gather information about the ECS estate. These operations are scoped to discovery and assessment.
  • [REMOTE_CODE_EXECUTION]: The skill utilizes a local Python script, tools/report_to_html.py, for converting Markdown reports to HTML. Analysis of the script confirms it is self-contained, lacks external dependencies, and includes robust security controls such as HTML escaping and a URL scheme allowlist to mitigate XSS and malicious redirection risks.
  • [DATA_EXFILTRATION]: No data exfiltration patterns were detected. The skill is designed to write its assessment reports to the local workspace and does not instruct the agent to transmit data to external or untrusted network locations.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 14, 2026, 11:00 AM
Security Audit — agent-trust-hub — ecs-operation-review