AD security-hardener
One-command OpenClaw security audit, scoring, and auto-remediation. Addresses CVE-2026-33579 and common misconfigurations. Scans for exposed API keys, weak file permissions, unauthenticated endpoints, unsafe plugin configs, insecure transport settings, and missing auth. Generates a 0-100 security score with severity-ranked findings and auto-fixes what it can. Use when asked to "harden my OpenClaw", "security audit", "am I secure", "fix my security", "security score", "check for exposed keys", "audit my agent", "CVE check", "lock down my instance", or when setting up a new OpenClaw installation and want to verify security posture before going live.
One-command OpenClaw security audit, scoring, and auto-remediation.
As a process D 41/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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: 4. 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 41/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 85Steps. 19 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 717 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
- +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
- +5Description quotes 9 example trigger phrases
- +3Description length 655: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 19 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.