docker-expert
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local shell commands and Docker CLI tools (
docker build,docker run,docker exec) to detect environments and validate project configurations. - [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: Reads and analyzes local project files such as
Dockerfileanddocker-compose.ymlto adapt its strategy. - Boundary markers: Absent; the skill does not explicitly instruct the agent to treat content within project files as untrusted data.
- Capability inventory: High; the agent is authorized to build images, run containers, and execute commands within them using the Docker CLI.
- Sanitization: Absent; the skill processes local file content directly to perform its primary functions.
Audit Metadata