docker-expert
Pass
Audited by Gen Agent Trust Hub on Apr 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses diagnostic shell commands like
docker infoanddocker psto gather container environment data. - [COMMAND_EXECUTION]: It performs
docker buildanddocker runto validate Dockerfiles, which involves executing containerized code based on local files. - [PROMPT_INJECTION]: The skill ingests local configuration files (e.g., Dockerfiles) to tailor its recommendations.
- Ingestion points: Reads
Dockerfile*and*compose*.ymlviafind(SKILL.md). - Boundary markers: None.
- Capability inventory:
docker build,docker run,docker exec(SKILL.md). - Sanitization: None.
Audit Metadata