FF openclaw-docs

Complete OpenClaw documentation reference. Use when you need information about OpenClaw configuration, CLI commands, channel setup, tools, concepts, or any OpenClaw-related questions. Includes 264 pages covering automation, channels (WhatsApp/Telegram/Discord/iMessage/Signal/Slack/etc), CLI commands, core concepts, gateway configuration, installation guides, model providers, tools, and more.

Not recommendedcritical or high security findings · low grade F

ClawHub Agent Skills author: Douglas v1.0.1 80 files body ≈ 1 373 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 33/100 · Will not run — References files that are not bundled: references/index.md, references/start/getting-started.md, references/start/setup.md

Reference Discord Telegram WhatsApp Slack Writing and documentstype 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

30/100

safety, quality, tests

Safety 60%: 0
Quality 40%: 76
Run on models: none yet

Process rating

33/100

Will not run

References files that are not bundled: references/index.md, references/start/getting-started.md, references/start/setup.md

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.

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.

Exfiltration

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.

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

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.
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 · 71

high Obfuscation uni-zero-width references/automation/auth-monitoring.md:26

Zero-width / invisible characters (possible hidden text) (3 occurrences)
```
␀Auth monitoring
```
high Obfuscation uni-zero-width references/automation/cron-jobs.md:54

Zero-width / invisible characters (possible hidden text) (31 occurrences)
```
␀Cron jobs (Gateway scheduler)
```
high Obfuscation uni-zero-width references/automation/cron-vs-heartbeat.md:47

Zero-width / invisible characters (possible hidden text) (24 occurrences)
```
␀Cron vs Heartbeat: When to Use Each
```
high Obfuscation uni-zero-width references/automation/gmail-pubsub.md:33

Zero-width / invisible characters (possible hidden text) (10 occurrences)
```
␀Gmail Pub/Sub -> OpenClaw
```
high Obfuscation uni-zero-width references/automation/hooks.md:88

Zero-width / invisible characters (possible hidden text) (65 occurrences)
```
␀Hooks
```
high Obfuscation uni-zero-width references/automation/poll.md:29

Zero-width / invisible characters (possible hidden text) (6 occurrences)
```
␀Polls
```
high Obfuscation uni-zero-width references/automation/troubleshooting.md:29

Zero-width / invisible characters (possible hidden text) (6 occurrences)
```
␀Automation troubleshooting
```
high Obfuscation uni-zero-width references/automation/webhook.md:35

Zero-width / invisible characters (possible hidden text) (12 occurrences)
```
␀Webhooks
```
high Obfuscation uni-zero-width references/channels.md:16

Zero-width / invisible characters (possible hidden text) (3 occurrences)
```
␀Chat Channels
```
high Obfuscation uni-zero-width references/channels/broadcast-groups.md:52

Zero-width / invisible characters (possible hidden text) (39 occurrences)
```
␀Broadcast Groups
```
high Obfuscation uni-zero-width references/channels/channel-routing.md:22

Zero-width / invisible characters (possible hidden text) (9 occurrences)
```
␀Channels & routing
```
high Obfuscation uni-zero-width references/channels/discord.md:29

Zero-width / invisible characters (possible hidden text) (16 occurrences)
```
␀Discord (Bot API)
```
high Obfuscation uni-zero-width references/channels/feishu.md:63

Zero-width / invisible characters (possible hidden text) (50 occurrences)
```
␀Feishu bot
```
high Obfuscation uni-zero-width references/channels/googlechat.md:26

Zero-width / invisible characters (possible hidden text) (13 occurrences)
```
␀Google Chat (Chat API)
```
high Obfuscation uni-zero-width references/channels/grammy.md:26

Zero-width / invisible characters (possible hidden text) (3 occurrences)
```
␀grammY Integration (Telegram Bot API)
```
high Obfuscation uni-zero-width references/channels/group-messages.md:20

Zero-width / invisible characters (possible hidden text) (7 occurrences)
```
␀Group messages (WhatsApp web channel)
```
high Obfuscation uni-zero-width references/channels/groups.md:26

Zero-width / invisible characters (possible hidden text) (13 occurrences)
```
␀Groups
```
high Obfuscation uni-zero-width references/channels/imessage.md:22

Zero-width / invisible characters (possible hidden text) (9 occurrences)
```
␀iMessage (legacy: imsg)
```
high Obfuscation uni-zero-width references/channels/irc.md:26

Zero-width / invisible characters (possible hidden text) (11 occurrences)
```
␀Quick start
```
high Obfuscation uni-zero-width references/channels/line.md:21

Zero-width / invisible characters (possible hidden text) (8 occurrences)
```
␀LINE (plugin)
```
high Obfuscation uni-zero-width references/channels/location.md:17

Zero-width / invisible characters (possible hidden text) (4 occurrences)
```
␀Channel location parsing
```
high Obfuscation uni-zero-width references/channels/matrix.md:25

Zero-width / invisible characters (possible hidden text) (12 occurrences)
```
␀Matrix (plugin)
```
high Obfuscation uni-zero-width references/channels/mattermost.md:23

Zero-width / invisible characters (possible hidden text) (10 occurrences)
```
␀Mattermost (plugin)
```
high Obfuscation uni-zero-width references/channels/msteams.md:63

Zero-width / invisible characters (possible hidden text) (50 occurrences)
```
␀Microsoft Teams (plugin)
```
high Exfiltration exfil-webhook-url references/channels/msteams.md:260

Webhook / callback URL commonly used for exfiltration (verify the destination)
```
# Set messaging endpoint to: https://abc1….io/api/messages
```
high Obfuscation uni-zero-width references/channels/pairing.md:23

Zero-width / invisible characters (possible hidden text) (10 occurrences)
```
␀Pairing
```
high Obfuscation uni-zero-width references/channels/signal.md:31

Zero-width / invisible characters (possible hidden text) (18 occurrences)
```
␀Signal (signal-cli)
```
high Obfuscation uni-zero-width references/channels/slack.md:27

Zero-width / invisible characters (possible hidden text) (14 occurrences)
```
␀Slack
```
high Obfuscation uni-zero-width references/channels/telegram.md:22

Zero-width / invisible characters (possible hidden text) (14 occurrences)
```
␀Telegram (Bot API)
```
high Obfuscation uni-zero-width references/channels/troubleshooting.md:29

Zero-width / invisible characters (possible hidden text) (16 occurrences)
```
␀Channel troubleshooting
```
high Obfuscation uni-zero-width references/channels/whatsapp.md:27

Zero-width / invisible characters (possible hidden text) (14 occurrences)
```
␀WhatsApp (Web channel)
```
high Obfuscation uni-zero-width references/channels/zalo.md:30

Zero-width / invisible characters (possible hidden text) (17 occurrences)
```
␀Zalo (Bot API)
```
high Obfuscation uni-zero-width references/channels/zalouser.md:25

Zero-width / invisible characters (possible hidden text) (12 occurrences)
```
␀Zalo Personal (unofficial)
```
high Obfuscation uni-zero-width references/ci.md:28

Zero-width / invisible characters (possible hidden text) (5 occurrences)
```
␀CI Pipeline
```
high Obfuscation uni-zero-width references/cli.md:89

Zero-width / invisible characters (possible hidden text) (66 occurrences)
```
␀CLI reference
```
high Obfuscation uni-zero-width references/cli/agents.md:27

Zero-width / invisible characters (possible hidden text) (4 occurrences)
```
␀`openclaw agents`
```
high Obfuscation uni-zero-width references/cli/approvals.md:28

Zero-width / invisible characters (possible hidden text) (5 occurrences)
```
␀`openclaw approvals`
```
high Obfuscation uni-zero-width references/cli/browser.md:31

Zero-width / invisible characters (possible hidden text) (8 occurrences)
```
␀`openclaw browser`
```
high Obfuscation uni-zero-width references/cli/channels.md:30

Zero-width / invisible characters (possible hidden text) (7 occurrences)
```
␀`openclaw channels`
```
high Obfuscation uni-zero-width references/cli/directory.md:31

Zero-width / invisible characters (possible hidden text) (8 occurrences)
```
␀`openclaw directory`
```
high Obfuscation uni-zero-width references/cli/doctor.md:26

Zero-width / invisible characters (possible hidden text) (3 occurrences)
```
␀`openclaw doctor`
```
high Obfuscation uni-zero-width references/cli/gateway.md:35

Zero-width / invisible characters (possible hidden text) (12 occurrences)
```
␀Gateway CLI
```
high Obfuscation uni-zero-width references/cli/hooks.md:36

Zero-width / invisible characters (possible hidden text) (13 occurrences)
```
␀`openclaw hooks`
```
high Obfuscation uni-zero-width references/cli/memory.md:26

Zero-width / invisible characters (possible hidden text) (3 occurrences)
```
␀`openclaw memory`
```
high Obfuscation uni-zero-width references/cli/message.md:36

Zero-width / invisible characters (possible hidden text) (13 occurrences)
```
␀`openclaw message`
```
high Obfuscation uni-zero-width references/cli/models.md:28

Zero-width / invisible characters (possible hidden text) (5 occurrences)
```
␀`openclaw models`
```
high Obfuscation uni-zero-width references/cli/nodes.md:27

Zero-width / invisible characters (possible hidden text) (4 occurrences)
```
␀`openclaw nodes`
```
high Obfuscation uni-zero-width references/cli/onboard.md:27

Zero-width / invisible characters (possible hidden text) (4 occurrences)
```
␀`openclaw onboard`
```
high Obfuscation uni-zero-width references/cli/plugins.md:28

Zero-width / invisible characters (possible hidden text) (5 occurrences)
```
␀`openclaw plugins`
```
high Obfuscation uni-zero-width references/cli/sandbox.md:37

Zero-width / invisible characters (possible hidden text) (14 occurrences)
```
␀Sandbox CLI
```
high Obfuscation uni-zero-width references/cli/system.md:29

Zero-width / invisible characters (possible hidden text) (6 occurrences)
```
␀`openclaw system`
```
high Obfuscation uni-zero-width references/cli/update.md:32

Zero-width / invisible characters (possible hidden text) (9 occurrences)
```
␀`openclaw update`
```
high Obfuscation uni-zero-width references/cli/voicecall.md:26

Zero-width / invisible characters (possible hidden text) (3 occurrences)
```
␀`openclaw voicecall`
```
high Obfuscation uni-zero-width references/concepts/agent-loop.md:34

Zero-width / invisible characters (possible hidden text) (17 occurrences)
```
␀Agent Loop (OpenClaw)
```
high Obfuscation uni-zero-width references/concepts/agent-workspace.md:29

Zero-width / invisible characters (possible hidden text) (12 occurrences)
```
␀Agent workspace
```
high Obfuscation uni-zero-width references/concepts/agent.md:29

Zero-width / invisible characters (possible hidden text) (9 occurrences)
```
␀Workspace (required)
```
high Obfuscation uni-zero-width references/concepts/architecture.md:31

Zero-width / invisible characters (possible hidden text) (14 occurrences)
```
␀Gateway architecture
```
high Obfuscation uni-zero-width references/concepts/compaction.md:25

Zero-width / invisible characters (possible hidden text) (8 occurrences)
```
␀Context Window & Compaction
```
high Obfuscation uni-zero-width references/concepts/context.md:30

Zero-width / invisible characters (possible hidden text) (13 occurrences)
```
␀Context
```
high Obfuscation uni-zero-width references/concepts/markdown-formatting.md:34

Zero-width / invisible characters (possible hidden text) (11 occurrences)
```
␀Markdown formatting
```

…and 2 more

Medium and low: 9

medium Exfiltration exfil-webhook-url references/channels/msteams.md:259

Webhook / callback URL commonly used for exfiltration (verify the destination) (security demo / example)
```
# Copy the https URL, e.g., https://abc1….io
```
demo
medium Exfiltration net-credential-use references/channels/msteams.md:659

Credential used in a network call (verify the destination is the intended service)
```
curl -H "Authorization: Bearer $TOKEN" \
```
medium Exfiltration net-credential-use references/channels/msteams.md:663

Credential used in a network call (verify the destination is the intended service)
```
curl -H "Authorization: Bearer $TOKEN" \
```
medium Broad scope meta-agent-memory-dump references/cli/memory.md

Agent memory / workspace files bundled with the skill (2) — likely a workspace dump with personal data or tokens
```
references/cli/memory.md, references/concepts/memory.md
```
low Secrets in code secret-high-entropy-token references/channels/groups.md:15

High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
```
- [Pattern: personal DMs + public groups (single agent)](#pattern-personal-dms-%2B-p…ent)
```
detector
low Secrets in code secret-high-entropy-token references/channels/groups.md:19

High-entropy token-like string (may be an id, hash or a credential)
```
- [Group/channel tool restrictions (optional)](#group%2Fch…nal)
```
low Secrets in code secret-high-entropy-token references/channels/msteams.md:35

High-entropy token-like string (may be an id, hash or a credential)
```
- [With Teams RSC + Microsoft Graph Application permissions](#with-teams-rsc-%2B-m…ons)
```
low Secrets in code secret-high-entropy-token references/channels/msteams.md:37

High-entropy token-like string (may be an id, hash or a credential)
```
- [Graph-enabled media + history (required for channels)](#graph-enabled-media-%2B-h…els)
```
low Exfiltration exfil-webhook-url references/channels/telegram.md:104

Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
```
curl "https://api.telegram.org/bot<bot_token>/getUpdates"
```
placeholder

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: references/index.md
warning missing-ref reference to a missing file: references/start/getting-started.md
warning missing-ref reference to a missing file: references/start/setup.md
warning missing-ref reference to a missing file: references/start/wizard.md
warning missing-ref reference to a missing file: references/start/bootstrapping.md
warning missing-ref reference to a missing file: references/install.md
warning missing-ref reference to a missing file: references/install/node.md
warning missing-ref reference to a missing file: references/install/docker.md
warning missing-ref reference to a missing file: references/install/ansible.md
warning missing-ref reference to a missing file: references/install/updating.md
warning missing-ref reference to a missing file: references/tools.md
warning missing-ref reference to a missing file: references/tools/exec.md
warning missing-ref reference to a missing file: references/tools/browser.md
warning missing-ref reference to a missing file: references/tools/skills.md
warning missing-ref reference to a missing file: references/tools/subagents.md
warning missing-ref reference to a missing file: references/gateway.md
warning missing-ref reference to a missing file: references/gateway/configuration.md
warning missing-ref reference to a missing file: references/gateway/authentication.md
warning missing-ref reference to a missing file: references/gateway/remote.md
warning missing-ref reference to a missing file: references/gateway/security.md
warning missing-ref reference to a missing file: references/providers.md
warning missing-ref reference to a missing file: references/providers/anthropic.md
warning missing-ref reference to a missing file: references/providers/openai.md
warning missing-ref reference to a missing file: references/providers/openrouter.md
warning missing-ref reference to a missing file: references/providers/litellm.md
warning missing-ref reference to a missing file: references/concepts/session.md
warning missing-ref reference to a missing file: references/concepts/multi-agent.md
warning missing-ref reference to a missing file: references/concepts/models.md
warning missing-ref reference to a missing file: references/help/faq.md
warning missing-ref reference to a missing file: references/help/troubleshooting.md
warning missing-ref reference to a missing file: references/help/environment.md

Process rating: all ten parameters 33/100

Will not run. References files that are not bundled: references/index.md, references/start/getting-started.md, references/start/setup.md

0Tools and files. 31 referenced file(s) missing: references/index.md, references/start/getting-started.md, references/start/setup.md
0Result and completion. Does not say what the result is
0Inputs and preconditions. Does not say what the process needs to start
0Failures and branches. Linear process with no failure handling
0Progress reporting. Says nothing while it works
20When it triggers. No condition that starts the skill
30Running it twice. 1 mutating operations with no state check
100Steps. 53 steps
100Consistency. Name and required fields are in place
100Execution cost. Instruction body is 1373 tokens

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
+1No license
+2Single-language instructions
+3Description length 394: enough signal without eating the budget
+4Structure: 15 headings
+3Step-by-step instructions: 53 items
+4Has examples (1 code blocks)
+4Reference files are cited in the instructions (2 of 3)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.

External checks

ClawHub: clean

This is a static OpenClaw documentation bundle that describes powerful features, but the skill itself does not install code, run commands, or hide behavior.

LLM: benign (high) · VirusTotal: · 29 May 2026

Tests

— no evals.json

— no spec.yaml

— not run on models

Files · 80

references/automation/auth-monitoring.md 2K
references/automation/cron-jobs.md 19K
references/automation/cron-vs-heartbeat.md 12K
references/automation/gmail-pubsub.md 8K
references/automation/hooks.md 23K
references/automation/poll.md 3K
references/automation/troubleshooting.md 5K
references/automation/webhook.md 9K
references/channels/broadcast-groups.md 12K
references/channels/channel-routing.md 4K
references/channels/discord.md 19K
references/channels/feishu.md 14K
references/channels/googlechat.md 10K
references/channels/grammy.md 4K
references/channels/group-messages.md 6K
references/channels/groups.md 12K
references/channels/imessage.md 8K
references/channels/irc.md 7K
references/channels/line.md 5K
references/channels/location.md 2K
references/channels/matrix.md 12K
references/channels/mattermost.md 4K
references/channels/msteams.md 32K
references/channels/pairing.md 4K
references/channels/signal.md 13K
references/channels/slack.md 14K
references/channels/telegram.md 22K
references/channels/troubleshooting.md 5K
references/channels/whatsapp.md 12K
references/channels/zalo.md 8K
references/channels/zalouser.md 5K
references/channels.md 3K
references/ci.md 2K
references/cli/agent.md 2K
references/cli/agents.md 3K
references/cli/approvals.md 3K
references/cli/browser.md 4K
references/cli/channels.md 4K
references/cli/configure.md 2K
references/cli/cron.md 2K
references/cli/dashboard.md 1K
references/cli/directory.md 3K
references/cli/dns.md 1K
references/cli/docs.md 1K
references/cli/doctor.md 2K
references/cli/gateway.md 8K
references/cli/health.md 1K
references/cli/hooks.md 7K
references/cli/logs.md 1K
references/cli/memory.md 2K
references/cli/message.md 9K
references/cli/models.md 4K
references/cli/nodes.md 3K
references/cli/onboard.md 3K
references/cli/pairing.md 1K
references/cli/plugins.md 3K
references/cli/reset.md 1K
references/cli/sandbox.md 6K
references/cli/security.md 2K
references/cli/sessions.md 1K

Dates

In catalog since 17 Feb 2026

Updated in catalog 11 May 2026

First seen here 10 Sept 2026

Last analysis 11 Sept 2026, 02:46 UTC

Last seen in crawl 24 h ago

Score history

Date		Score	Safety	Qual.
11 Sept 2026	F	30	0	76
10 Sept 2026	F	0	0	0

Similar skills

B openclaw-docs modbender/skill-library-mcp
B openclaw-docs ClawHub
B openclaw-docs ClawHub