AB audit-openclaw-security
Audit and harden OpenClaw deployments and interpret `openclaw security audit` findings. Use when the user wants to secure OpenClaw, review gateway exposure/auth/reverse proxies/Tailscale Serve or Funnel, check DM/group access (pairing, allowlists, mention gating, `session.dmScope`), minimise tool permissions and sandboxing, review plugins/skills/secrets/transcripts/log retention, or lock down Docker/macOS/laptop/EC2 installs. Not for generic OS, Docker, or cloud hardening unrelated to OpenClaw.
As a process B 73/100 · Nearly there — weak spots: inputs and preconditions, running it twice
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 · 0
✓ No critical or high findings
Files scanned: 15. 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 73/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 5 mutating operations with no state check
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 145 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3501 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 12 top-level sections: this looks like several domains in one skill
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
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 499: enough signal without eating the budget
- +4Structure: 34 headings
- +3Step-by-step instructions: 145 items
- +4Has examples (11 code blocks)
- +4Reference files are cited in the instructions (7 of 7)
- +3All 3 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.