ansible

An autonomous security-testing agent for Ansible and AWX, tools used to automate server configuration and deployments. It examines the configuration-management system and its connected resources.

In plain words
What is it for?
Use it to test inventories, playbooks, encrypted Ansible Vault data, privilege escalation settings, and the AWX or Automation Controller API.
Why use it?
It helps find security problems in automation settings that can affect many servers or applications at once.

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/ansible
Clone the repo
git clone --depth 1 https://github.com/ASCIT31/Dark-Moon
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,266 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 $0.00044 $0.06266
Opus 5 $0.00022 $0.03133
Sonnet 5 $0.00009 $0.01253
Haiku 4.5 $0.00004 $0.00627

Measured 3d ago against content hash 3b8b0a677b02, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

ansible 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 3d ago.

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 -u "$AWX_USER:$AWX_PASS" -X POST <awx_url>/api/v2/job_templates/<id>/launch/ -H 'Content-Type: application/json' -d '{}'

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

Unrestricted tool accesslowExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

primitive (shell/command/raw/script modules run arbitrary commands on every

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.

call and its raw output. Use curl+jq for the AWX/Controller REST API, grep for
conf/agents/ansible.md · 451 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. 3d ago First seen · 451 lines · 44 tokens per session scan B 3b8b0a677b02

Subscribe to this mod's changes

ansible is an agent published in the GitHub repository ASCIT31/Dark-Moon (886 stars, last pushed 4d ago), licensed GPL-3.0. It adds 44 tokens to every session and 6,266 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, unrestricted tool access, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.