SKILLEMALL.ai
RU Sign in

BC server-mate

Build or extend a lightweight server monitoring and AI operations workflow for Linux hosts running Nginx or Apache, with optional centralized remote monitoring through the BT-Panel (Baota) HTTP API. Use when Codex needs to collect psutil metrics, parse access, error, or auth logs (locally OR pulled remotely from BT panels with no probe on the target host), design JSON payloads or APIs, add webhook alerts, generate PDF ops reports with SSL expiry summaries, answer natural-language monitoring questions, or implement guarded auto-ban and auto-heal behaviors.

ClawHub Agent Skills author: tankeito v1.6.1 MIT-0 19 files · 1 script body ≈ 5 144 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process C 56/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureInfrastructuretype 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
B
77/100
safety, quality, tests
Safety 60%
79
Quality 40%
74
Run on models
none yet
Process rating
C
56/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

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. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 13

✓ No critical or high findings

Medium and low: 13
  • medium Exfiltration exfil-webhook-url scripts/webhook_center.py:52
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    channel_config["url"] = f"https://api.telegram.org/bot{bot_token}/sendMessage"
    quoted
  • medium Exfiltration exfil-webhook-url scripts/webhook_center.py:214
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    url = f"https://api.telegram.org/bot{bot_token}/sendDocument"
    quoted
  • low Dangerous commands cmd-background-process assets/bootstrap_node.sh:78
    Starts a background / autostarted process
    systemctl enable server-mate.service
  • low Dangerous commands cmd-cron-mention README_ZH.md:389
    Mentions editing / listing crontab (documentation of a security skill)
    crontab -e
    security skill
  • low Dangerous commands cmd-cron-mention README.md:389
    Mentions editing / listing crontab (documentation of a security skill)
    crontab -e
    security skill
  • low Dangerous commands cmd-cron-mention user-guide.md:560
    Mentions editing / listing crontab (documentation of a security skill)
    crontab -e
    security skill
  • low Dangerous commands cmd-privilege user-guide.md:642
    Privilege escalation / world-writable permissions (documentation of a security skill)
    python3 ./scripts/server_agent.py --config ./config.yaml --generate-service | sudo tee /etc/systemd/system/server-mate.service >/dev/null
    security skill
  • low Dangerous commands cmd-background-process user-guide.md:647
    Starts a background / autostarted process (documentation of a security skill)
    sudo systemctl enable --now server-mate.service
    security skill
  • low Dangerous commands cmd-background-process user-guide.md:714
    Starts a background / autostarted process (documentation of a security skill)
    sudo systemctl enable --now server-mate-weekly-report.timer
    security skill
  • low Dangerous commands cmd-pipe-to-shell-known-host user-guide.md:979
    Pipe-to-shell installer from a well-known host (still executes remote code) (documentation of a security skill)
    curl -sSL https://raw.githubusercontent.com/tankeito/server-mate/main/assets/bootstrap_node.sh | sudo bash
    security skill
  • low Dangerous commands cmd-privilege user-guide.md:979
    Privilege escalation / world-writable permissions (documentation of a security skill)
    curl -sSL https://raw.githubusercontent.com/tankeito/server-mate/main/assets/bootstrap_node.sh | sudo bash
    security skill
  • low Dangerous commands cmd-privilege user-guide.md:998
    Privilege escalation / world-writable permissions (documentation of a security skill)
    python3 scripts/server_agent.py --config ./config.yaml --generate-service | sudo tee /etc/systemd/system/server-mate.service > /dev/null
    security skill
  • low Dangerous commands cmd-background-process user-guide.md:1000
    Starts a background / autostarted process (documentation of a security skill)
    sudo systemctl enable --now server-mate.service
    security skill

Files scanned: 18. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 5144 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 56/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
  • 70Execution cost. Instruction body is 5144 tokens
  • 100Steps. 126 steps
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 15 top-level sections: this looks like several domains in one skill

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
  • -32 of 5 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 561: enough signal without eating the budget
  • +4Structure: 16 headings
  • +3Step-by-step instructions: 126 items
  • +4Has examples (1 code blocks)
  • +4Reference files are cited in the instructions (4 of 4)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.

External checks

ClawHub: suspicious
Server-Mate is a real monitoring tool, but it asks for production-level server authority and exposes several high-impact features with weak default scoping or hardening.
LLM: suspicious (high) · VirusTotal: · 3 Jul 2026