SKILLEMALL.ai
GitHub ↗ RU Sign in

FD proxmox-dc-lifecycle

Rebuild, replace, demote, reinstall, rejoin, or re-promote a Windows Active Directory domain controller VM on Proxmox: demote it, clean metadata from a healthy DC, reinstall via autounattend, then promote it again. Use for Proxmox-hosted DC rebuild requests and symptoms that point to rebuild: NTDS will not start, ntds.dit is missing, promotion fails with trust-relationship or "no computer account" errors, demotion hangs, dcdiag/replication fails on one DC, or a broken DC VM needs to come back. Also use for Windows AD operations through QEMU guest agent (qm guest exec). Rule: do not corrupt Active Directory; verify replication and FSMO before and after every lifecycle step, change one DC at a time, and never destroy or recreate a VM while AD still has NTDS Settings for that DC.

Blockedguard blocked the skill: signs of malicious behaviour
ClawHub Agent Skills author: Eddy v1.0.4 MIT-0 14 files · 2 scripts body ≈ 3 039 tokens Open the sourceclawhub.ai↗ analyzed 15 d ago

Rebuild, replace, demote, reinstall, rejoin, or re-promote a Windows Active Directory domain controller VM on Proxmox: demote it, clean metadata from a…

As a process D 35/100 · Unfinished process — References files that are not bundled: assets/autounattend.xml.template

AnalyzerAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
F
34/100
safety, quality, tests
Safety 60%
0
Quality 40%
86
Run on models
none yet
Process rating
D
35/100
Unfinished process
References files that are not bundled: assets/autounattend.xml.template
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten
Guard blocked this skill: critical findings below. Do not install it until the author fixes them.

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

  1. Remove the critical guard findings (secrets, dangerous commands, hidden instructions): while they stand the skill is blocked and cannot grade above F.
  2. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 14

  • critical Dangerous commands cmd-encoded-exec references/qga-execution.md:15
    Executes a base64/encoded payload (quoted — discussed, not commanded)
    "\$d=[System.Text.Encoding]::UT…ing([Convert]::Fr…ing('$b64')); Invoke-Expression \$d" 2>&1
    quoted
  • critical Dangerous commands cmd-encoded-exec references/qga-execution.md:38
    Executes a base64/encoded payload (quoted — discussed, not commanded)
    "\$d=[System.Text.Encoding]::UT…ing([Convert]::Fr…ing('$B64')); Invoke-Expression \$d" 2>&1
    quoted
  • high Dangerous commands cmd-persistence references/demotion.md:44
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    $taskPw | schtasks /create /tn HDC_Demote /ru "<DOMAIN>\Administrator" /rp * /rl HIGHEST `
  • high Dangerous commands cmd-encoded-exec scripts/run-guest-ps.sh:19
    Executes a base64/encoded payload (string literal in code, not executed)
    decoder="\$d=[System.Text.Encoding]::UT…ing([Convert]::Fr…ing('$b64')); Invoke-Expression \$d"
    code literal
Medium and low: 10
  • medium Dangerous commands cmd-persistence references/gotchas.md:23
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    - **Fix (demote):** run the cmdlet via a **scheduled task whose run-as principal is the domain admin** (`schtasks /create /ru ... /rp *`, password via stdin), so it executes in a true logon session. (
    quoted
  • medium Dangerous commands cmd-persistence references/gotchas.md:68
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition)
    - **Signature:** `schtasks /create /ru <DOMAIN>\Administrator /rp * ...` errors "The trust relationship between this workstation and the primary domain failed."
    detector
  • medium Dangerous commands cmd-privilege references/os-reinstall.md:30
    Privilege escalation / world-writable permissions
    sudo cp /tmp/unattend.iso /mnt/pve/<isoStorage>/template/iso/unattend-<dc>.iso
  • medium Dangerous commands cmd-persistence references/promotion.md:9
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    - A **classic scheduled task** (`schtasks /create ... /sc ONCE /st <future> ; schtasks /run`) IS properly detached and survives the QGA call returning. Use it (once trust exists), or run a single sync
    quoted
  • medium Dangerous commands cmd-persistence references/qga-execution.md:55
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    - **Demotion (`Uninstall-ADDSDomainController`) on an existing domain member:** fails as SYSTEM with **LDAP error 58** ("server cannot perform the requested operation"), because SYSTEM never establish
    quoted
  • medium Dangerous commands cmd-persistence references/qga-execution.md:65
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    - **Scheduled task** (`schtasks /create /sc ONCE /st <future-time> ; schtasks /run`): properly detached — survives the QGA call returning. Use for ops that exceed the timeout. Needs a valid task princ
    quoted
  • medium Exfiltration net-credential-use references/qga-execution.md:76
    Credential used in a network call (verify the destination is the intended service)
    PID=$(curl -sk -H "Authorization: PVEAPIToken=$TOKENID=$SECRET" \
  • medium Exfiltration net-credential-use references/qga-execution.md:82
    Credential used in a network call (verify the destination is the intended service)
    curl -sk -H "Authorization: PVEAPIToken=$TOKENID=$SECRET" \
  • low Dangerous commands cmd-execpolicy-bypass references/demotion.md:45
    Runs PowerShell with execution policy bypassed (quoted — discussed, not commanded)
    /sc ONCE /st 00:00 /tr "powershell -NoProfile -ExecutionPolicy Bypass -File C:\Windows\Temp\.hdc\run.ps1" /f
    quoted
  • low Dangerous commands cmd-persistence references/gotchas.md:65
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (negated — the text forbids it)
    - **Fix:** detach with a **classic scheduled task** (`schtasks /create /sc ONCE /st <future> ; schtasks /run`) — it's owned by the task scheduler, not your QGA call — or run a single **long synchronou
    negated

Files scanned: 14. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: assets/autounattend.xml.template

Process rating: all ten parameters 35/100

Will not run. References files that are not bundled: assets/autounattend.xml.template
  • 0Tools and files. 1 referenced file(s) missing: assets/autounattend.xml.template
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 9 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 85Steps. 29 steps, 1 vague phrases
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3039 tokens
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low The response is described with custom markup (9 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +2Single-language instructions
  • +3Description length 787: enough signal without eating the budget
  • +4Structure: 14 headings
  • +3Step-by-step instructions: 29 items
  • +4Has examples (1 code blocks)
  • +4Reference files are cited in the instructions (8 of 8)
  • +3All 2 scripts are documented
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.

External checks

ClawHub: clean
This is a high-impact but coherent Active Directory/Proxmox runbook that discloses its privileged actions and includes safety gates rather than hidden behavior.
LLM: benign (high) · VirusTotal: · 30 Jun 2026