acc-create-docker-healthcheck

Warn

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: MEDIUMPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • Indirect Prompt Injection (MEDIUM): The skill possesses a vulnerability surface for indirect prompt injection through its code generation capabilities.
  • Ingestion points: The skill ingests untrusted data from the user/agent context, including service lists, stack details, and health check URLs in the 'Usage' section.
  • Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands within the user-provided data.
  • Capability inventory: The skill generates executable shell scripts (.sh) and Docker instructions (HEALTHCHECK CMD, RUN chmod +x) that are intended for execution within a container environment.
  • Sanitization: The skill does not define sanitization or validation logic for the user-provided URLs or service names before interpolating them into generated scripts.
  • Command Execution (LOW): The generated scripts utilize commands like curl, cgi-fcgi, and pgrep. While appropriate for health checks, these represent the capability set available to a potential injector.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 06:15 AM