SKILLEMALL.ai
GitHub ↗ RU Sign in

CF Codex Hook

OpenClaw 智能任务执行系统 - 支持任务派发、执行、监控（精简版）

ClawHub Agent Skills author: lonelybeanz v1.0.2 MIT-0 11 files · 8 scripts body ≈ 1 307 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 31/100 · Will not run — weak spots: result and completion, when it triggers, inputs and preconditions

ReferenceSoftware developmentInfrastructuretype 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
69/100
safety, quality, tests
Safety 60%
77
Quality 40%
57
Run on models
none yet
Process rating
F
31/100
Will not run
Result and completion w 14
0
When it triggers w 12
0
Inputs and preconditions w 11
0
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. 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 · 7

✓ No critical or high findings

Medium and low: 7
  • medium Exfiltration exfil-webhook-url scripts/auto-merge.sh:240
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    response=$(curl -s -X POST "https://api.telegram.org/bot$tg_token/sendMessage" \
    quoted
  • medium Exfiltration net-credential-use scripts/auto-merge.sh:240
    Credential used in a network call (verify the destination is the intended service)
    response=$(curl -s -X POST "https://api.telegram.org/bot$tg_token/sendMessage" \
  • medium Exfiltration exfil-webhook-url SKILL.md:236
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    DISCORD_WEBHOOK="https://discord.com/api/webhooks/xxx"
    quoted
  • medium Exfiltration exfil-webhook-url SKILL.md:255
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    export DISCORD_WEBHOOK="https://discord.com/api/webhooks/xxx"
    quoted
  • low Exfiltration exfil-webhook-url scripts/notify.sh:41
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    local url="https://api.telegram.org/bot$TELEGRAM_BOT_TOKEN/sendMessage"
    placeholder
  • low Exfiltration read-dotenv SKILL.md:202
    Reads a .env file
    export $(cat ~/.openclaw/.env | xargs) && codex-tasks monitor-start 60 &
  • low Exfiltration read-dotenv SKILL.md:243
    Reads a .env file
    export $(cat ~/.openclaw/.env | xargs) && codex-tasks monitor-start

Files scanned: 11. 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 description-short description under 40 chars: too little signal for triggering
  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 31/100

  • 0Result and completion. Does not say what the result is
  • 0When it triggers. No condition that starts the skill
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 30Running it twice. 1 mutating operations with no state check
  • 40Consistency. Frontmatter name (Codex Hook) differs from the folder (codex-hook)
  • 50Steps. 2 steps
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 100Execution cost. Instruction body is 1307 tokens
  • 100Progress reporting. Reports progress
  • low The response is described with custom markup (8 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)
  • +3Description length 37: 120–800 characters recommended
  • +3No numbered steps or checklist
  • +3Output format is not stated: the model decides each time
  • +2Single-language instructions
  • +4Structure: 30 headings
  • +4Has examples (18 code blocks)
  • +3All 8 scripts are documented
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 57.

External checks

ClawHub: suspicious
This skill is a task automation tool, but it can run coding agents, restart work, push and merge pull requests, delete branches, and send task details externally without enough safeguards.
LLM: suspicious (high) · VirusTotal: · 29 May 2026