AC clawscan
perform first-pass security checks for openclaw deployments by registering the client, checking whether the installed clawscan package is outdated, checking whether the current openclaw version matches known vulnerable versions, checking whether installed skills match known malicious hashes, and checking whether openclaw or related services are listening on 0.0.0.0 or other non-local interfaces. use this skill when a user asks to assess whether openclaw is safe, run a clawscan check, verify openclaw version risk, verify skills hashes, or review listening ports and exposure risk.
As a process C 62/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, consistency
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 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".
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Concealment
en-hide-from-userSKILL.md:184Instruction to hide actions from the user (documentation of a security skill)- If every check returns risk level `low` and no actionable finding is present → **produce no output**. Do not tell the user "all clear" unless they explicitly ask for a status.
security skill
Files scanned: 7. 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 62/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (clawscan) differs from the folder (clawscan-autosec-dev)
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 72 steps
- 100Failures and branches. 8 branches, has a failure section
- 100Execution cost. Instruction body is 2284 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
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)
- +1No license
- +2Single-language instructions
- +3Description length 585: enough signal without eating the budget
- +4Structure: 22 headings
- +3Step-by-step instructions: 72 items
- +3Output format is stated explicitly
- +4Has examples (10 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.