SKILLEMALL.ai
GitHub ↗ RU Sign in

FF team-dispatch

Use when a request requires multi-agent workflow orchestration (task decomposition + dependency/DAG + parallel execution), needs durable task tracking across context compaction, or needs retries/fallbacks and completion notifications.

Not recommendedcritical or high security findings · low grade F
ClawHub Agent Skills author: vvusu v1.0.8 MIT-0 80 files · 10 scripts body ≈ 3 116 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 40/100 · Will not run — References files that are not bundled: scripts/watch.sh

ProcedureAI 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
26/100
safety, quality, tests
Safety 60%
0
Quality 40%
65
Run on models
none yet
Process rating
F
40/100
Will not run
References files that are not bundled: scripts/watch.sh
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

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.

Broad scope 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 asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

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. 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 · 16

  • high Dangerous commands cmd-persistence assets/windows/watch-install.ps1.txt:24
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    Register-ScheduledTask -TaskName $TaskName -Action $Action -Trigger $Trigger -Principal $Principal -Force | Out-Null
  • high Dangerous commands cmd-persistence scripts/watch-install.sh:221
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    run launchctl bootstrap "gui/$(id -u)" "$PLIST_DST"
  • high Dangerous commands cmd-persistence scripts/watch-uninstall.sh:107
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    printf '%s\n' "$NEW" | crontab -
Medium and low: 13
  • medium Broad scope meta-agent-memory-dump assets/agents/coder/workspace/HEARTBEAT.md
    Agent memory / workspace files bundled with the skill (28) — likely a workspace dump with personal data or tokens
    assets/agents/coder/workspace/HEARTBEAT.md, assets/agents/coder/workspace/IDENTITY.md, assets/agents/coder/workspace/SOUL.md, assets/agents/coder/workspace/USER.md, assets/agents/product/workspace/HEA
  • medium Dangerous commands cmd-execpolicy-bypass assets/windows/watch-install.ps1.txt:3
    Runs PowerShell with execution policy bypassed
    #   powershell -ExecutionPolicy Bypass -File .\assets\windows\watc…ps1
  • medium Dangerous commands cmd-execpolicy-bypass assets/windows/watch-install.ps1.txt:4
    Runs PowerShell with execution policy bypassed
    #   $env:INTERVAL="120"; $env:GRACE="20"; powershell -ExecutionPolicy Bypass -File .\assets\windows\watc…ps1
  • medium Dangerous commands cmd-persistence CHANGELOG.md:31
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    - fix(Clawhub): 将 plist 改为模板 `assets/launchd/openclaw.team-dispatch.watch.plist.xml`，安装时渲染到 `~/Library/LaunchAgents/` 再 bootstrap（避免 Clawhub 过滤 .plist）
    quoted
  • medium Dangerous commands cmd-persistence CHANGELOG.md:41
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    - fix(macOS): watcher 安装改为先渲染绝对路径 LaunchAgent plist 到 `~/Library/LaunchAgents/` 再 bootstrap
    quoted
  • medium Dangerous commands cmd-persistence scripts/watch-install.sh:5
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (code comment)
    # - Linux: systemd --user service (preferred) or crontab @reboot fallback
    comment
  • medium Dangerous commands cmd-persistence scripts/watch-install.sh:41
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    PLIST_DST="$HOME/Library/LaunchAgents/openclaw.team-dispatch.watch.plist"
    code literal
  • medium Dangerous commands cmd-persistence scripts/watch-install.sh:261
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (code comment)
    # Fallback: install @reboot entry that starts watch.sh in background.
    comment
  • medium Dangerous commands cmd-persistence scripts/watch-install.sh:263
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    LINE="@reboot INTERVAL=$INTERVAL GRACE=$GRACE /bin/bash $SKILL_DIR/scripts/watch.sh >> $HOME/.openclaw/workspace/tasks/watch.out.log 2>> $HOME/.openclaw/workspace/tasks/watch.err.log &"
    code literal
  • medium Dangerous commands cmd-persistence scripts/watch-uninstall.sh:102
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    CURRENT="$(crontab -l 2>/dev/null || true)"
    code literal
  • low Dangerous commands cmd-cron-mention scripts/watch-install.sh:266
    Mentions editing / listing crontab (string literal in code, not executed)
    CURRENT="$(crontab -l 2>/dev/null || true)"
    code literal
  • low Dangerous commands cmd-cron-mention scripts/watch-uninstall.sh:102
    Mentions editing / listing crontab (string literal in code, not executed)
    CURRENT="$(crontab -l 2>/dev/null || true)"
    code literal
  • low Dangerous commands cmd-execpolicy-bypass SKILL.md:474
    Runs PowerShell with execution policy bypassed (documentation table row)
    | `assets/windows/watch-install.ps1.txt` | Windows 安装 watcher（Scheduled Task） | `copy <SKILL_DIR>\\assets\\windows\\watch-install.ps1.txt watc…ps1; powershell -ExecutionPolicy Bypass -File .\
    table

Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: scripts/watch.sh

Process rating: all ten parameters 40/100

Will not run. References files that are not bundled: scripts/watch.sh
  • 0Tools and files. 1 referenced file(s) missing: scripts/watch.sh
  • 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
  • 50Failures and branches. 0 branches, has a failure section
  • 100Steps. 24 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3116 tokens
  • 100Running it twice. No mutating operations
  • low 15 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (14 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
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • -226 emoji in the instructions: noise for the model
  • -42 reference files, but SKILL.md never points to them: the model will not open them
  • -35 of 12 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 234: enough signal without eating the budget
  • +4Structure: 49 headings
  • +3Step-by-step instructions: 24 items
  • +4Has examples (27 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.

External checks

ClawHub: suspicious
This skill is mostly a disclosed multi-agent orchestrator, but it also makes broad OpenClaw configuration changes, installs recurring background jobs, and includes unrelated onboarding instructions that collect personal/contact details.
LLM: suspicious (high) · VirusTotal: · 29 May 2026