FF claw-wiki
Reference and refresh a local OpenClaw documentation snapshot for product usage, deployment, configuration, CLI commands, channels, gateway behavior, tools, troubleshooting, and docs-version verification. Use when users ask how OpenClaw works, how to configure or operate it, where a feature is documented, whether the local docs are outdated, or to update this skill's OpenClaw knowledge base from upstream docs.
As a process F 43/100 · Will not run — References files that are not bundled: references/update-workflow.md, references/routing-cheatsheet.md, references/query-examples.md
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.
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.
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.
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".
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.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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.
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.
- 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 · 14
-
high Dangerous commands
cmd-persistenceopenclaw_docs/channels/bluebubbles.md:123Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl unload ~/Library/LaunchAgents/com.user.poke-messages.plist 2>/dev/null || true
-
high Dangerous commands
cmd-persistenceopenclaw_docs/channels/bluebubbles.md:124Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl load ~/Library/LaunchAgents/com.user.poke-messages.plist
-
high Exfiltration
exfil-webhook-urlopenclaw_docs/channels/msteams.md:203Webhook / callback URL commonly used for exfiltration (verify the destination)# Set messaging endpoint to: https://abc1….io/api/messages
Medium and low: 11
-
medium Dangerous commands
cmd-persistenceopenclaw_docs/channels/bluebubbles.md:84Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)- `~/Library/LaunchAgents/com.user.poke-messages.plist`
quoted -
medium Exfiltration
exfil-webhook-urlopenclaw_docs/channels/msteams.md:202Webhook / 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-useopenclaw_docs/channels/msteams.md:557Credential used in a network call (verify the destination is the intended service)curl -H "Authorization: Bearer $TOKEN" \
-
medium Exfiltration
net-credential-useopenclaw_docs/channels/msteams.md:561Credential used in a network call (verify the destination is the intended service)curl -H "Authorization: Bearer $TOKEN" \
-
medium Broad scope
meta-agent-memory-dumpopenclaw_docs/cli/memory.mdAgent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokensopenclaw_docs/cli/memory.md
-
low Exfiltration
exfil-webhook-urlopenclaw_docs/channels/telegram.md:135Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)curl "https://api.telegram.org/bot<bot_token>/getUpdates"
placeholder -
low Secrets in code
secret-password-literalopenclaw_docs/channels/twitch.md:54Hard-coded password / key literal (may be an example) (placeholder value)accessToken: "oaut…...", // OAuth Access Token (or use OPENCLAW_TWITCH_ACCESS_TOKEN env var)
placeholder -
low Secrets in code
secret-password-literalopenclaw_docs/channels/twitch.md:98Hard-coded password / key literal (may be an example) (placeholder value)accessToken: "oaut…...",
placeholder -
low Secrets in code
secret-password-literalopenclaw_docs/channels/twitch.md:160Hard-coded password / key literal (may be an example) (placeholder value)accessToken: "oaut…...",
placeholder -
low Secrets in code
secret-password-literalopenclaw_docs/channels/twitch.md:166Hard-coded password / key literal (may be an example) (placeholder value)accessToken: "oaut…...",
placeholder -
low Secrets in code
secret-password-literalopenclaw_docs/channels/twitch.md:321Hard-coded password / key literal (may be an example) (placeholder value)accessToken: "oaut…...",
placeholder
Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/update-workflow.md - warning
missing-refreference to a missing file: references/routing-cheatsheet.md - warning
missing-refreference to a missing file: references/query-examples.md
Process rating: all ten parameters 43/100
- 0Tools and files. 3 referenced file(s) missing: references/update-workflow.md, references/routing-cheatsheet.md, references/query-examples.md
- 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
- 30Running it twice. 8 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 7 branches
- 85Steps. 66 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1520 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 413: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 66 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.