ecs-task-definition-creator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [Metadata Poisoning] (SAFE): Metadata is descriptive and consistent with the skill's functionality. No deceptive patterns found.
  • [Indirect Prompt Injection] (SAFE): The skill processes user input for AWS configurations; however, no malicious interpolation or lack of boundary awareness was observed in the static definition. Evidence: 1. Ingestion points: User requests via triggers. 2. Boundary markers: Absent. 3. Capability inventory: Bash(aws:*), Write, Edit tools. 4. Sanitization: Absent.
  • [No Code] (SAFE): The skill contains no executable scripts or external dependencies, significantly reducing the risk of malicious behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:37 PM