docker-expert
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Employs standard Docker CLI tools (docker info, docker build, docker run) for environment discovery and configuration validation. These operations are local and consistent with the skill's stated DevOps purpose.
- [DATA_EXFILTRATION]: Enumerates local project files like Dockerfiles and Compose files using the find command. This metadata remains within the agent context and is used to provide relevant recommendations.
- [PROMPT_INJECTION]: Analyzes user-provided configuration files. Ingestion points: Local files via find/cat. Boundary markers: Absent. Capability inventory: Local Docker and shell execution. Sanitization: Absent. This established pattern for auditing user projects is a surface for indirect prompt injection but is required for the skill's primary function.
Audit Metadata