AD openclaw-security
⚠️ HIGH PRIVILEGE SECURITY AUDIT SKILL Performs comprehensive security auditing for OpenClaw deployments. Requires system-level access for legitimate security scanning purposes. All operations are read-only and local-only. Covers: environment isolation, privilege checks, port exposure, skill trust sources, version checks, process monitoring, sensitive directory changes, cron jobs, SSH audits, file integrity baselines, yellow-line operation audits, disk usage, environment variable leak detection, DLP scanning (private key/mnemonic detection), skill/MCP integrity tracking, and disaster recovery backups. Use when: security audits, firewall/SSH/update hardening, risk posture review, exposure assessment, or periodic security checks on machines running OpenClaw (laptop, workstation, Pi, VPS).
As a process D 47/100 · Unfinished process — weak spots: when it triggers, inputs and preconditions, failures and branches
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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Risky intent
intent-offensive-securitySECURITY.md:72Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| Privilege escalation | Script checks and warns if running as root |
A further 1 matches are quotations in this security skill's documentation and are not counted as 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 47/100
- 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. 5 mutating operations with no state check
- 40Consistency. Frontmatter name (openclaw-security) differs from the folder (security-audit-openclaw)
- 60Tools and files. Uses tools (git) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 12 steps
- 100Execution cost. Instruction body is 999 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 806: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 16 headings
- +3Step-by-step instructions: 12 items
- +3Output format is stated explicitly
- +4Has examples (5 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.