Docker Manager

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This appears to be a legitimate Docker management skill, but it can run powerful Docker actions like forced cleanup, deletion, and container command execution without built-in confirmation.

Install only if you want the agent to administer Docker on this machine. Before allowing stop, remove, prune, or exec actions, confirm the exact container/image/volume and understand that cleanup commands may remove resources without another prompt.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Risk analysis

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

A mistaken or overly broad cleanup command could remove Docker resources and disrupt local development or services.

Why it was flagged

The prune implementation can force broad Docker cleanup without Docker's normal confirmation prompt, including image and volume prune paths elsewhere in the same function.

Skill content
run_cmd([DOCKER_CMD, "system", "prune", "-a", "-f"])
Recommendation

Require explicit user confirmation before stop/delete/prune operations, avoid force flags by default, and prefer named-resource or dry-run workflows for cleanup.

What this means

Commands run inside containers may change application state, files, or running processes.

Why it was flagged

The skill can execute a user-supplied command inside a selected Docker container. This is purpose-aligned for Docker administration, but it is still a powerful capability.

Skill content
cmd = [DOCKER_CMD, "exec", "-it", args.name] + args.cmd.split()
Recommendation

Only run container exec commands when the target container and command are explicitly chosen and understood.

What this means

If installed where Docker access is equivalent to administrative control, the skill can affect containers, images, volumes, and potentially host-adjacent resources.

Why it was flagged

Using the Docker CLI means the skill operates with the caller's Docker daemon permissions, which can be highly privileged on many systems.

Skill content
"requires": {"bins": ["python3", "docker"]}
Recommendation

Use this only in environments where the agent is allowed to administer Docker, and avoid granting Docker access on sensitive hosts unless necessary.

What this means

Users have less external context for maintainer trust or update provenance.

Why it was flagged

The package has no declared upstream source or homepage, making provenance harder to verify even though the included code is visible.

Skill content
Source: unknown; Homepage: none
Recommendation

Review the included script before use and prefer a trusted, traceable source for administrative tooling.