SKILLEMALL.ai

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).

ClawHub Agent Skills author: iaadoa v1.0.2 MIT-0 4 files body ≈ 999 tokens Open the sourceclawhub.ai analyzed 2 d ago

As a process D 47/100 · Unfinished process — weak spots: when it triggers, inputs and preconditions, failures and branches

AnalyzerInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
A
94/100
safety, quality, tests
Safety 60%
98
Quality 40%
87
Run on models
none yet
Process rating
D
47/100
Unfinished process
Inputs and preconditions w 11
0
Failures and branches w 10
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • 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-security SECURITY.md:72
      Offensive-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.

    External checks

    ClawHub: clean
    This is a high-privilege security audit skill with broad local inspection, local report/baseline writes, and clearly opt-in Git/Telegram features that users should enable only deliberately.
    LLM: benign (medium) · VirusTotal: · 29 May 2026