The Agent Skills Directory

[SAFE] (SAFE): The skill follows security best practices for containerization, including the use of multi-stage builds, non-root users, and secret avoidance.
[NO_CODE] (SAFE): There are no executable scripts, shell commands, or network operations included in the skill. It functions entirely as a set of instructions for the AI agent.
[PROMPT_INJECTION] (SAFE): No instructions designed to bypass safety filters or override system prompts were identified.
[DATA_EXFILTRATION] (SAFE): No patterns for accessing sensitive files or sending data to external servers were detected.
[INDIRECT_PROMPT_INJECTION] (SAFE): While the skill processes user-provided descriptions of applications to generate Dockerfiles, it lacks the execution capabilities (e.g., subprocess calls, file writes) necessary to manifest a security risk from malicious user input.

docker-expert