SKILLEMALL.ai
RU Sign in

DC mcp-orchestral

MCP Server Orchestral Integration - Integriert den fortgeschrittenen MCP Server mit 27-28 Super-Agenten in das Super-Skill-Ökosystem. Ermöglicht DeepMaster-Agent-Orchestrierung, Flowise-Integration, MongoDB-Management und Multi-Agenten-Koordinierung.

Not recommendedcritical or high security findings · low grade D
ClawHub Agent Skills author: Faton Duaku v1.0.0 80 files body ≈ 3 374 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationMongoDBAI 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
D
43/100
safety, quality, tests
Safety 60%
25
Quality 40%
70
Run on models
none yet
Process rating
C
51/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

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.

Obfuscation
If you install

The files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.

For the author

Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.

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.

Secrets in code 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 files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.

For the author

The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 25

  • high Obfuscation uni-zero-width 2026-02-05-skill-creation.md:9
    Zero-width / invisible characters (possible hidden text) (3 occurrences)
    user: erstelle diese skills Noch zu erstellen: ContextMaster - Kontext-Verständnis CreativeBoost – Kreativität Fehleranalyse␀ UserAdaptation - Benutzeranpassung…
  • high Dangerous commands cmd-pipe-to-shell Administrator_Guide.md:71
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    curl -sfL https://get.k3s.io | sh -
Medium and low: 23
  • medium Secrets in code secret-labelled-token Code-Assistenten Anleitung_ n8n MCP Server mit UI.md:1502
    Labelled token / key literal (vendor format unknown — verify it is not a live credential)
    SECRET_KEY=n8n-…ion
  • medium Dangerous commands cmd-privilege DeepALL RAG – Ubuntu Sandbox System.md:730
    Privilege escalation / world-writable permissions
    sudo bash scripts/install_rootless_docker.sh
  • medium Dangerous commands cmd-privilege DEPLOYMENT_GUIDE.md:115
    Privilege escalation / world-writable permissions
    sudo chown -R clawd:clawd /home/clawd/clawd
  • medium Dangerous commands cmd-privilege DEPLOYMENT_GUIDE.md:569
    Privilege escalation / world-writable permissions
    sudo chown -R clawd:clawd /home/clawd/clawd
  • low Dangerous commands cmd-cron-mention AUTOMATION_GUIDE.md:306
    Mentions editing / listing crontab
    crontab -e
  • low Dangerous commands cmd-cron-mention AUTOMATION_GUIDE.md:345
    Mentions editing / listing crontab
    crontab -l
  • low Secrets in code secret-password-literal Code-Assistenten Anleitung_ n8n MCP Server mit UI.md:1502
    Hard-coded password / key literal (may be an example)
    SECRET_KEY=n8n-…ion
  • low Exfiltration read-dotenv Code-Assistenten Anleitung_ n8n MCP Server mit UI.md:1507
    Reads a .env file
    with open('.env', 'w') as f:
  • low Secrets in code secret-password-literal DeepALL RAG – Ubuntu Sandbox System.md:194
    Hard-coded password / key literal (may be an example)
    API_KEY=supe…123
  • low Exfiltration read-dotenv DeepALL RAG – Ubuntu Sandbox System.md:386
    Reads a .env file
    cp .env.example .env
  • low Secrets in code secret-password-literal DeepALL RAG – Ubuntu Sandbox System.md:393
    Hard-coded password / key literal (may be an example) (quoted — discussed, not commanded)
    curl -H "x-api-key: supe…123" http://SERVER:8088/health
    quoted
  • low Secrets in code secret-password-literal DeepALL RAG – Ubuntu Sandbox System.md:397
    Hard-coded password / key literal (may be an example) (quoted — discussed, not commanded)
    -H "Content-Type: application/json" -H "x-api-key: supe…123" \
    quoted
  • low Secrets in code secret-password-literal DeepALL RAG – Ubuntu Sandbox System.md:406
    Hard-coded password / key literal (may be an example) (quoted — discussed, not commanded)
    curl -H "x-api-key: supe…123" http://SERVER:8088/sandboxes/sandbox-XXXXX/logs
    quoted
  • low Secrets in code secret-password-literal DeepALL RAG – Ubuntu Sandbox System.md:409
    Hard-coded password / key literal (may be an example) (quoted — discussed, not commanded)
    curl -X DELETE -H "x-api-key: supe…123" http://SERVER:8088/sandboxes/sandbox-XXXXX
    quoted
  • low Exfiltration read-dotenv DeepALL RAG – Ubuntu Sandbox System.md:727
    Reads a .env file
    cp config/.env.example config/.env
  • low Secrets in code secret-high-entropy-token DEEPSYNAPTICA_MULTI_AGENT_INTEGRATION_PLAN.md:54
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "real_g": "asst…PCY",
    quoted
  • low Secrets in code secret-high-entropy-token DEEPSYNAPTICA_MULTI_AGENT_INTEGRATION_PLAN.md:55
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "si_agent": "asst…F8d",
    quoted
  • low Secrets in code secret-high-entropy-token DEEPSYNAPTICA_MULTI_AGENT_INTEGRATION_PLAN.md:56
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "deepall_code": "asst…Nuy"
    quoted
  • low Secrets in code secret-high-entropy-token DEEPSYNAPTICA_MULTI_AGENT_INTEGRATION_PLAN.md:65
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    export OPENAI_ASSISTANT_REAL_G="asst…PCY"
    quoted
  • low Secrets in code secret-high-entropy-token DEEPSYNAPTICA_MULTI_AGENT_INTEGRATION_PLAN.md:66
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    export OPENAI_ASSISTANT_SI_AGENT="asst…F8d"
    quoted
  • low Exfiltration read-dotenv DEPLOYMENT_GUIDE.md:564
    Reads a .env file
    source /home/clawd/clawd/.env
  • low Exfiltration read-dotenv ENHANCED_CLAWD_README.md:92
    Reads a .env file
    cp .env.template .env
  • low Exfiltration read-dotenv ENHANCED_CLAWDBOT_2.0.0_ULTIMATE.md:92
    Reads a .env file
    cp .env.template .env

Files scanned: 78. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 51/100

  • 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. 2 mutating operations with no state check
  • 40Consistency. Frontmatter name (mcp-orchestral) differs from the folder (clawdbot-knowledge)
  • 50Failures and branches. 0 branches, has a failure section
  • 100Tools and files. No external tools needed
  • 100Steps. 71 steps
  • 100Execution cost. Instruction body is 3374 tokens
  • low 12 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
  • -222 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +3Description length 250: enough signal without eating the budget
  • +4Structure: 44 headings
  • +3Step-by-step instructions: 71 items
  • +4Has examples (13 code blocks)

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

External checks

ClawHub: suspicious
This skill needs Review because it bundles a broad autonomous agent system with file, command, database, and deployment authority that is not clearly bounded by its MCP-orchestration description.
LLM: suspicious (high) · VirusTotal: suspicious · 28 May 2026