BB ocuclaw-assist
Guide OcuClaw install, update, rollback, and troubleshooting — covering the OpenClaw plugin, the phone app, Tailscale private networking between phone and host, and optional Soniox voice-input, Even AI, and bug-report integrations. Use when the user wants OcuClaw set up, a version change, or hits setup/connection failures.
Guide OcuClaw install, update, rollback, and troubleshooting — covering the OpenClaw plugin, the phone app, Tailscale private networking between phone and…
As a process B 65/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
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 tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
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.
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.
- 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 · 4
-
high Concealment
en-hide-from-userSKILL.md:73Instruction to hide actions from the userCopy this into your first reply and tick each box as you finish it. Do not tell the user setup is complete while any REQUIRED box is unchecked. A genuinely blocked box → mark `[blocked: reason]` and s
Medium and low: 3
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostreferences/fresh-install.md:194Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://tailscale.com/install.sh | sh
-
medium Dangerous commands
cmd-privilegereferences/troubleshooting.md:130Privilege escalation / world-writable permissionssudo chown -R 1000:1000 /path/to/openclaw-config /path/to/openclaw-workspace
-
low Dangerous commands
cmd-privilegereferences/troubleshooting.md:132Privilege escalation / world-writable permissions (quoted — discussed, not commanded)If OpenClaw intentionally runs as root, repair the managed plugin root to root ownership instead (`sudo chown -R root:root /path/to/openclaw-config/npm`). Then `openclaw plugins registry --refresh` (o
quoted
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 65/100
- 0Result and completion. Does not say what the result is
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 3 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 31 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3149 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (3 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
- +1No license
- +2Single-language instructions
- +3Description length 324: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 31 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (6 of 6)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.