docker-expert
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses system commands including
docker info,docker ps,find, anddocker-composeto analyze the local environment. It also performs build and run operations (docker build,docker run) to validate the Docker configurations found in the workspace.- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by ingesting and processing content from the local file system that could contain malicious instructions. - Ingestion points: The skill searches for and builds from local Dockerfiles and configuration files using
find .anddocker build .(SKILL.md). - Boundary markers: Absent. The skill does not use delimiters to isolate local data from its internal instruction logic.
- Capability inventory: The skill can execute commands on the host and within containers using
docker build,docker run, anddocker exec(SKILL.md). - Sanitization: Absent. No validation is performed on the contents of the Dockerfiles or project files before they are built or executed.
Audit Metadata