ansible

SAFE max severity MEDIUMSkillSpector Do not install 65 registry clawhub.ai last scanned 2026-02-05 1 scan

Verdict safe, but 1 finding (1 medium), mainly data exfiltration. Most recent scan 2026-02-05.

This Ansible infrastructure automation skill is generally well-structured and secure for its intended purpose. The skill provides legitimate infrastructure-as-code capabilities without malicious code or prompt injection attempts. The primary security concern is the documentation's treatment of SSH password authentication, which could lead users to implement insecure credential storage if not properly understood. The skill appropriately requires external binary dependencies (ansible, ansible-playbook) and provides comprehensive documentation. Missing optional metadata fields reduce transparency but don't represent active security threats. The skill follows infrastructure automation best practices and includes security-focused roles (SSH hardening, fail2ban, UFW firewall). No data exfiltration, command injection, or malicious behavior detected.
Scanner's overall assessment (LLM analyzer)

Findings1

Critical0

High0

Medium1

Low0

Analyzersstatic behavioral llm trigger meta

Second scanner: NVIDIA SkillSpector

VerdictDo not install 65

Score65 / 100

Issues36

CategoriesPrivilege Escalation Rogue Agent

Version2.12.0 (static)

The two scanners disagree: Cisco found nothing and SkillSpector says do not install. One of them has a blind spot here; read the skill before trusting either. How the two scanners compare across the whole corpus: Two scanners, one corpus.

What this skill does

Infrastructure automation with Ansible. Use for server provisioning, configuration management, application deployment, and multi-host orchestration. Includes playbooks for OpenClaw VPS setup, security hardening, and common server configurations.

Package: 20 files, 54 KB
SKILL.md: 1268 words, 12+ sections
Code: None. Instructions only.
Requires: bins: ansible ansible-playbook

SKILL.md covers: Ansible Skill · Quick Start · Prerequisites · Install Ansible · Or on macOS · Verify · Run Your First Playbook · Test connection · Run playbook · Dry run (check mode) · With specific tags · Directory Structure

Findings

MEDIUM Hardcoded SSH Password in Inventory Example Data Exfiltrationllm

The SKILL.md documentation contains an example inventory configuration that demonstrates storing SSH passwords in plain text using ansible_ssh_pass with vault variables. While the example references vault encryption, it teaches users a pattern that could lead to credential exposure if they store passwords without proper vault encryption or commit unencrypted credentials.

SKILL.md

ansible_ssh_pass: "{{ vault_eva_password }}" - Example shows password-based authentication pattern that users might implement insecurely

Remediation: Update documentation to emphasize SSH key-based authentication as the primary method. If password authentication examples are needed, add prominent warnings about vault encryption requirements and never storing passwords in plain text. Consider removing password-based examples entirely in favor of key-based authentication patterns.

What is in the package

File	Kind	Size
`SKILL.md`	doc	11 KB
`ansible.cfg`	config	606 B
`inventory/hosts.yml`	config	1.6 KB
`playbooks/openclaw-vps.yml`	config	9.0 KB
`playbooks/security.yml`	config	391 B
`playbooks/site.yml`	config	630 B
`references/best-practices.md`	doc	4.9 KB
`references/modules-cheatsheet.md`	doc	6.6 KB
`references/troubleshooting.md`	doc	6.4 KB
`inventory/group_vars/all.yml`	config	520 B
`roles/common/defaults/main.yml`	config	514 B
`roles/common/tasks/main.yml`	config	1.7 KB
`roles/nodejs/defaults/main.yml`	config	386 B
`roles/nodejs/tasks/main.yml`	config	1.9 KB
`roles/openclaw/defaults/main.yml`	config	628 B
`roles/openclaw/handlers/main.yml`	config	253 B
`roles/openclaw/tasks/main.yml`	config	3.6 KB
`roles/security/defaults/main.yml`	config	568 B
`roles/security/handlers/main.yml`	config	206 B
`roles/security/tasks/main.yml`	config	3.4 KB

External hosts referenced

deb.nodesource.com github.com docs.ansible.com galaxy.ansible.com www.ansiblefordevops.com

Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.

Environment variables referenced

PASSWORD

Package contents recorded 2026-10-22. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.

What we checked

Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
Behavioral analyzer. Checks what the skill asks the agent to do against what its description claims it does.
Llm analyzer. A language model reads the skill and reports intent-level issues the rules cannot express.
Trigger analyzer. Looks for instructions that fire on conditions the user did not ask for.
Meta analyzer. A second model pass that validates, deduplicates and re-scores the other analyzers' findings.

What we did not check

Runtime behaviour. The skill was not executed; findings come from reading its files.
Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
Content the analyzers cannot read: images, binaries, and some non-English text.
Known scanner bypass classes. See the methodology and limitations page.

Sources

Repository: https://clawhub.ai/skills/ansible-skill
Raw scan result: ansible-scan.json
Badge for your README: ![skillscan.io](https://skillscan.io/badge/clawhub-ai-ansible.svg)
Request a re-scan