BC openclaw
Comprehensive guide for installing, configuring, operating, and troubleshooting OpenClaw — a self-hosted, multi-channel AI agent gateway. Use when the user asks about OpenClaw setup, configuration, channel management (WhatsApp/Telegram/Discord/Slack/iMessage/etc.), model provider setup, Gateway operations, multi-agent routing, security hardening, troubleshooting, or any maintenance task related to their local OpenClaw installation. Also use when encountering errors from `openclaw` CLI commands or the Gateway daemon.
As a process C 50/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
The same skill appears in 1 more place: ClawHub
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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.
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
- 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 · 12
✓ No critical or high findings
Medium and low: 12
-
medium Dangerous commands
cmd-persistencereferences/gateway_ops.md:339Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation of a security skill)launchctl bootstrap gui/$(id -u) ~/Library/LaunchAgents/ai.openclaw.gateway.plist
security skill -
medium Broad scope
meta-agent-memory-dumpreferences/heartbeat.mdAgent memory / workspace files bundled with the skill (2) — likely a workspace dump with personal data or tokensreferences/heartbeat.md, references/memory.md
-
low Concealment
en-hide-from-userreferences/exec.md:38Instruction to hide actions from the user (negated — the text forbids it)- **Sandboxing off + `host=sandbox`**: Exec fails closed (does not silently run on gateway). Enable sandboxing or use `host=gateway` with approvals.
negated -
low Dangerous commands
cmd-background-processreferences/gateway_ops.md:77Starts a background / autostarted process (documentation of a security skill)sudo systemctl enable --now openclaw-gateway.service
security skill -
low Dangerous commands
cmd-pipe-to-shellreferences/gateway_ops.md:208Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill; the skill's own vendor host)curl -fsSL https://openclaw.ai/install.sh | bash
security skillvendor-host -
low Exfiltration
read-dotenvreferences/gateway_ops.md:298Reads a .env file (documentation of a security skill)cat ~/.openclaw/.env
security skill -
low Dangerous commands
cmd-pipe-to-shellreferences/install.md:26Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill; the skill's own vendor host)curl -fsSL https://openclaw.ai/install.sh | bash
security skillvendor-host -
low Dangerous commands
cmd-pipe-to-shellreferences/install.md:35Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill; the skill's own vendor host)curl -fsSL https://openclaw.ai/install.sh | bash -s -- --no-onboard
security skillvendor-host -
low Dangerous commands
cmd-pipe-to-shellreferences/install.md:127Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill; the skill's own vendor host)curl -fsSL https://openclaw.ai/install.sh | bash
security skillvendor-host -
low Dangerous commands
cmd-pipe-to-shellSKILL.md:279Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill; the skill's own vendor host)curl -fsSL https://openclaw.ai/install.sh | bash
security skillvendor-host
A further 2 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 55. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 50/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (openclaw) differs from the folder (bengii-gemini-fix)
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 4624 tokens
- 100Steps. 27 steps
- 100Progress reporting. Reports progress
- 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
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +3Description length 521: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 27 items
- +4Has examples (11 code blocks)
- +4Reference files are cited in the instructions (51 of 51)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.