SKILLEMALL.ai
GitHub ↗ RU Sign in

CC TeamClaw

A high-performance Agent subsystem designed for complex multi-agent orchestration (OASIS),visual multi-agent workflow orchestration, automated computer use tasks, and real-timevisual monitoring via a dedicated Web UI. Supports multi-vendor LLM backends(DeepSeek / OpenAI / Gemini / Claude etc.), social platform bot integrations (Telegram, QQ),and optional Cloudflare Tunnel for secure HTTPS public access to the Web UI from mobileor remote devices.

ClawHub Agent Skills author: hou xinyuan v1.0.0 58 files · 8 scripts body ≈ 9 525 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 54/100 · Has gaps — weak spots: result and completion, when it triggers, consistency

ProcedureTelegramCloudflareAI 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
C
60/100
safety, quality, tests
Safety 60%
61
Quality 40%
59
Run on models
none yet
Process rating
C
54/100
Has gaps
Result and completion w 14
0
When it triggers w 12
20
Consistency w 8
40
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.

Dangerous commands 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 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.

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 · 15

✓ No critical or high findings

Medium and low: 15
  • medium Exfiltration net-redirectable-api-key chatbot/QQbot.py:22
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • medium Exfiltration net-redirectable-api-key chatbot/telegrambot.py:14
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • medium Exfiltration net-redirectable-api-key oasis/server.py:703
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • medium Dangerous commands cmd-pipe-to-shell-known-host scripts/setup_env.sh:17
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -LsSf https://astral.sh/uv/install.sh | sh
  • medium Exfiltration net-redirectable-api-key src/llm_factory.py:84
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • medium Exfiltration net-redirectable-api-key src/mainagent.py:553
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • low Obfuscation obf-hex-escape-chain README_tmp.html:1063
    Escaped/char-code string obfuscation (quoted — discussed, not commanded)
    <h3 id="2-oasis-%E6%99%BA%E8%83%BD%E7%BC%96%E6%8E%92%E5%8F%AF%E7%BC%96%E7%A8%8B%E7%9A%84%E4%B8%93%E5%AE%B6%E5%8D%8F%E4%BD%9C%E5%BC%95%E6%93%8E">2. OASIS 智能编排——可编程的专家协作引擎</h3>
    quoted
  • low Obfuscation obf-hex-escape-chain README_tmp.html:1223
    Escaped/char-code string obfuscation (quoted — discussed, not commanded)
    <h4 id="%E4%B8%A4%E7%A7%8D%E4%B8%93%E5%AE%B6%E8%BF%90%E8%A1%8C%E6%A8%A1%E5%BC%8F">两种专家运行模式</h4>
    quoted
  • low Secrets in code secret-password-literal selfskill/scripts/adduser.py:28
    Hard-coded password / key literal (may be an example)
    username, password = sys.argv[1], sys.argv[2]
  • low Dangerous commands cmd-background-process selfskill/scripts/run.sh:46
    Starts a background / autostarted process
    nohup python scripts/launcher.py > "$PROJECT_ROOT/logs/launcher.log" 2>&1 &
  • low Exfiltration read-dotenv selfskill/scripts/run.sh:53
    Reads a .env file
    source config/.env 2>/dev/null || true
  • low Exfiltration read-dotenv selfskill/scripts/run.sh:100
    Reads a .env file
    source config/.env 2>/dev/null || true
  • low Exfiltration exfil-webhook-url src/mcp_bark.py:114
    Webhook / callback URL commonly used for exfiltration (verify the destination) (security demo / example; quoted — discussed, not commanded)
    :param public_url: The public URL (e.g. "https://xxx.trycloudflare.com")
    demoquoted
  • low Dangerous commands cmd-privilege src/mcp_commander.py:94
    Privilege escalation / world-writable permissions (string literal in code, not executed)
    "> /dev/sd", "chmod 777 /", "chown root", "/etc/passwd", "/etc/shadow",
    code literal
  • low Exfiltration exfil-webhook-url src/mcp_telegram.py:24
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    TELEGRAM_API = f"https://api.telegram.org/bot{TELEGRAM_BOT_TOKEN}"
    placeholder

Files scanned: 56. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning body-long SKILL.md body ≈ 9525 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "user-invokable"

Process rating: all ten parameters 54/100

  • 0Result and completion. Does not say what the result is
  • 20When it triggers. No condition that starts the skill
  • 40Consistency. Frontmatter name (TeamClaw) differs from the folder (teamclawtest)
  • 40Execution cost. Instruction body is 9525 tokens: crowds the task out of the window
  • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
  • 60Failures and branches. 2 branches
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 98 steps
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • low 26 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
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • -2localhost URLs: will not work for another user
  • -37 of 7 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 449: enough signal without eating the budget
  • +4Structure: 74 headings
  • +3Step-by-step instructions: 98 items
  • +4Has examples (48 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 59.

External checks

ClawHub: suspicious
TeamClaw appears to be a real multi-agent service, but it gives agents and exposed web routes high-impact authority with weak scoping and some secret-handling risks.
LLM: suspicious (high) · VirusTotal: · 29 May 2026