docker-compose-manager

Fail

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The Linux installation metadata specifies fetching and executing the official Docker installation script from get.docker.com.
  • Evidence: 'linux: "curl -fsSL https://get.docker.com | sh && docker compose version"' in SKILL.md.
  • [COMMAND_EXECUTION]: The skill performs shell commands using the docker compose CLI to manage containerized services.
  • Evidence: Core capabilities in SKILL.md include commands such as 'docker compose up', 'docker compose ps', and 'docker compose down'.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external docker-compose.yml files which could contain instructions intended to influence the agent if the files are from untrusted sources.
  • Ingestion points: 'compose_file' input parameter in SKILL.md.
  • Boundary markers: None identified.
  • Capability inventory: Shell execution of 'docker compose' commands as described in SKILL.md.
  • Sanitization: No explicit validation or sanitization of the compose file content is specified.
Recommendations
  • HIGH: Downloads and executes remote code from: https://get.docker.com - DO NOT USE without thorough review
Audit Metadata
Risk Level
HIGH
Analyzed
Aug 31, 2026, 07:16 AM
Security Audit — agent-trust-hub — docker-compose-manager