Claude Code, Skill
Wazuh Autopilot
Wazuh Autopilot, a skill listed in the PlugVet directory.
Compatibility: Not stated.
Grade D
Two or more Medium findings, or a High finding. Only try it in a sandbox.
Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.
Rescanned at commit 07da85f90cf7, unchanged since the check below.
INSTALL_REMOTE_SCRIPT SECRETS_PATH_CREDENTIAL AGENT_IGNORE_INSTRUCTIONS
Why this grade
- INSTALL_REMOTE_SCRIPT Medium
Fetches a script from the network and runs it (a pipe to a shell, or an install hook with a URL).
docs/TAILSCALE_MANDATORY.md, line 26
curl -fsSL https://tailscale.com/install.sh | sh - SECRETS_PATH_CREDENTIAL Medium
Mentions a credential store path (~/.ssh, id_rsa, .npmrc, .aws/credentials, credentials.json, .netrc).
backend/app/skills/ir-playbook-bruteforce/references/playbook.md, line 1317
cat ~/.ssh/authorized_keys - AGENT_IGNORE_INSTRUCTIONS Medium
Text tells the agent to ignore earlier instructions.
backend/app/roster.py, line 303
"input": "Triage this Wazuh alert: {\"rule\":{\"id\":\"31106\",\"level\":12,\"description\":\"Web attack returned code 200\"},\"agent\":{\"id\":\"002\",\"name\":\"web-prod-02\"},\"
Any High, or two or more Medium findings, give D. One Medium gives C. Low findings or a security Note give B. Each code names a finding behind the letter.
If you think this grade is wrong, email [email protected] with the entry link and your evidence. We aim to acknowledge within two working days and decide within seven. If we confirm an error, we aim to correct it within 24 hours of confirming it. These are aims, not guarantees.
Grades are a hygiene check of the source at the commit shown, on the date checked, not a security audit or a guarantee. The free directory grades are automated. Before release, a PlugVet engineer reviews every paid report and any grade we hold back, including all F grades, against the source code and the evidence we quote.
What was checked
Plain notes from the hygiene checks.
Permissions
Note
requests shell access. The manifest names this permission.
PERMISSION_SHELL_DECLARED
backend/app/skills/ir-playbook-suspicious-powershell/references/playbook.md, line 698
- replace_aliases (iex→Invoke-Expression, icm→Invoke-Command)
backend/app/skills/ir-playbook-suspicious-powershell/references/playbook.md, line 746
- 'Invoke-Expression'
backend/app/skills/ir-playbook-suspicious-powershell/references/playbook.md, line 2039
- obfuscation: ["Invoke-Expression", "IEX", "[char[]]", "-join"]
Show more
backend/app/skills/ir-playbook-suspicious-powershell/SKILL.md, line 26
| In-memory / API abuse | rules 91810 (L10, CreateThread API), 91837 (L4, Invoke-Expression / Get-Content -Stream), 92151 (L12, PowerShell automation DLL loaded by a non-PowerShell
backend/app/skills/ir-playbook-suspicious-powershell/references/playbook.md, line 225
| **Invoke-Expression Chains** | `IEX(IEX(...))` | Nested IEX/ICM patterns | Critical |
Install and update
Serious
install fetches a script from the network.
INSTALL_REMOTE_SCRIPT
docs/TAILSCALE_MANDATORY.md, line 26
curl -fsSL https://tailscale.com/install.sh | sh
Network
Concern
can reach a host that is not written as a fixed address. can reach wazuh-manager. The description does not name that host. can reach firewall. The description does not name that host. can reach google.com. The description does not name that host.
NETWORK_NO_FIXED_HOST NETWORK_UNNAMED_HOST
backend/app/notify.py, line 16
r = httpx.post(url, json={"text": text}, timeout=10)
backend/app/skills/ir-playbook-lateral-movement/references/playbook.md, line 1074
curl -X POST "https://wazuh-manager:55000/active-response" \
backend/app/skills/ir-playbook-lateral-movement/references/playbook.md, line 1083
curl -X GET "https://wazuh-manager:55000/agents/${source_agent_id}" \
Show more
backend/app/skills/ir-playbook-lateral-movement/references/playbook.md, line 1109
curl -X POST "https://firewall/api/fmc_config/v1/domain/default/policy/accesspolicies/${policy_id}/accessrules" \
backend/app/skills/ir-playbook-privilege-escalation/references/playbook.md, line 299
logic: "curl/wget followed by chmod +x and execution within 2 minutes"
backend/app/skills/ir-playbook-privilege-escalation/references/playbook.md, line 671
test_command: "curl -m 5 https://google.com || echo 'Isolated'"
backend/app/swarm/mcp.py, line 54
resp = httpx.post(f"{self._base_url}/auth/token", json={"api_key": self._api_key},
backend/app/swarm/mcp.py, line 177
h = httpx.get(f"{base}/health", timeout=5, verify=settings.get("verify_tls", True)).json()
Dockerfile, line 24
CMD python -c "import urllib.request,sys; sys.exit(0 if urllib.request.urlopen('http://127.0.0.1:8080/health', timeout=4).status == 200 else 1)"
mock-wazuh/Dockerfile, line 16
CMD python -c "import urllib.request,json,sys; sys.exit(0 if json.load(urllib.request.urlopen('http://127.0.0.1:3000/health', timeout=4))['status']=='healthy' else 1)"
Secrets
Concern
reads a credential or environment file.
SECRETS_ENV_READ SECRETS_PATH_CREDENTIAL SECRETS_PATH_DOTENV
backend/app/config.py, line 24
self.secret_key = os.getenv("AUTOPILOT_SECRET_KEY") or self._persistent_secret()
backend/app/config.py, line 25
self.token_ttl_minutes = int(os.getenv("AUTOPILOT_TOKEN_TTL_MINUTES", "720"))
backend/app/skills/ir-playbook-bruteforce/references/playbook.md, line 1317
cat ~/.ssh/authorized_keys
Show more
backend/app/config.py, line 35
self.admin_password = os.getenv("AUTOPILOT_ADMIN_PASSWORD", "Autopilot!2026" if self.demo_mode else "")
backend/app/config.py, line 38
self.wazuh_mcp_api_key = os.getenv("WAZUH_MCP_API_KEY", "")
backend/app/config.py, line 42
self.model_api_key = os.getenv("MODEL_API_KEY", "")
backend/app/config.py, line 44
self.ingest_key = os.getenv("AUTOPILOT_INGEST_KEY", "")
backend/app/skills/ir-playbook-data-exfiltration/references/playbook.md, line 814
- .env
backend/app/skills/ir-playbook-privilege-escalation/references/playbook.md, line 550
- ssh_keys (~/.ssh/, C:\Users\*\.ssh\)
mock-wazuh/mock_wazuh/server.py, line 32
API_KEY = os.getenv("MOCK_API_KEY", "wazuh_demo_key")
mock-wazuh/mock_wazuh/server.py, line 33
API_KEY_SCOPES = os.getenv("MOCK_API_KEY_SCOPES", "wazuh:read wazuh:write").split()
mock-wazuh/mock_wazuh/sim.py, line 466
(31101, 5, "Web server 400 error code.", ["web", "accesslog"], "/.env", 404),
.dockerignore, line 8
*.md
.env.example, line 2
# Wazuh Autopilot - environment (copy to .env)
.gitignore, line 4
# Environment files (contain secrets)
.gitignore, line 5
.env
Agent instructions
Serious
instructions tell the agent to ignore earlier instructions.
AGENT_IGNORE_INSTRUCTIONS
backend/app/roster.py, line 303
"input": "Triage this Wazuh alert: {\"rule\":{\"id\":\"31106\",\"level\":12,\"description\":\"Web attack returned code 200\"},\"agent\":{\"id\":\"002\",\"name\":\"web-prod-02\"},\"
Obfuscation
Pass
No encoded or minified payload found.
Licence
Pass
A licence file is present (LICENSE).
Maintainer activity
Pass
The latest commit is within the last 365 days.
Note
Hygiene check of commit 07da85f90cf7. requests shell access. The manifest names this permission. install fetches a script from the network. can reach a host that is not written as a fixed address. can reach wazuh-manager. The description does not name that host. can reach firewall. The description does not name that host. can reach google.com. The description does not name that host. reads a credential or environment file. instructions tell the agent to ignore earlier instructions.
Date and source
Date checked:
github.com
Commit graded: 07da85f90cf7696f0e4783d5302980e12b268e59
This link goes to the original host. PlugVet does not host or check what you download from there, and installing it is your own decision and risk.