docker

An autonomous security-testing sub-agent for an exposed Docker Engine API, the interface used to manage Docker containers. It works with Docker images, containers, and possible container-to-host escape paths.

In plain words
What is it for?
Use it to perform penetration testing of exposed Docker Engine APIs and investigate images, containers, and possible paths from a container to its host.
Why use it?
It is intended to examine Docker access that may be reachable through a Unix socket or an unauthenticated network port, helping identify serious exposure risks.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/ascit31/dark-moon/docker
Clone the repo
git clone --depth 1 https://github.com/ASCIT31/Dark-Moon
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,187 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 3 findings. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00043 $0.06187
Opus 5 $0.00022 $0.03093
Sonnet 5 $0.00009 $0.01237
Haiku 4.5 $0.00004 $0.00619

Measured yesterday against content hash 264a1596602f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

docker scanned grade B with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Sends data to an external URLlowData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

curl -s --unix-socket /var/run/docker.sock -X POST http://localhost/containers/create -H 'Content-Type: application/json' -d '{"Image":"<local_image>","Cmd":["sleep","60"],"HostConfig":{"Binds":["/:/host"],"Privileged":t

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Reaches for credential filesmediumPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

- Exec into it and read a host-only file as proof (e.g. /etc/shadow via the

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl (either --unix-socket /var/run/docker.sock or a TCP host:port) plus jq
conf/agents/docker.md · 450 lines

The source is not reproduced here

Licensed GPL-3.0

The repository is licensed GPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 450 lines · 43 tokens per session scan B 264a1596602f

Subscribe to this mod's changes

docker is an agent published in the GitHub repository ASCIT31/Dark-Moon (878 stars, last pushed 3d ago), licensed GPL-3.0. It adds 43 tokens to every session and 6,187 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 3 findings (sends data to an external url, reaches for credential files, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.