SKILLEMALL.ai
RU Sign in

AB navil-audit

Deep security audit for OpenClaw. Run a comprehensive scan of all installed skills, MCP servers, and agent configuration. Generates a detailed security report with severity-ranked findings and remediation steps. Use when user says "audit my security", "deep scan", "full security check", "pentest my setup", "run security tests", "check for vulnerabilities", "am I safe", or "what MCP attacks would work against me". Also for CI/CD security gates and compliance reporting.

ClawHub Agent Skills author: ivanpantheon v1.0.2 MIT-0 4 files body ≈ 991 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process B 65/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice

AnalyzerGitHubAI and agentsSecurityInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
A
92/100
safety, quality, tests
Safety 60%
94
Quality 40%
89
Run on models
none yet
Process rating
B
65/100
Nearly there
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
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 · 6

    ✓ No critical or high findings

    Medium and low: 6
    • low Risky intent intent-offensive-security skill-card.md:20
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      Risk: Broad security prompts may trigger local scans or pentest-style commands against sensitive OpenClaw and MCP configuration. <br>
      detector
    • low Risky intent intent-offensive-security SKILL.md:3
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      description: Deep security audit for OpenClaw. Run a comprehensive scan of all installed skills, MCP servers, and agent configuration. Generates a detailed security report with severity-ranked finding
      detector
    • low Risky intent intent-offensive-security SKILL.md:30
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
      - User says "pentest" or "penetration test" or "attack simulation"
      quoted
    • low Risky intent intent-offensive-security SKILL.md:53
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ### Phase 2: Penetration Testing
    • low Risky intent intent-offensive-security SKILL.md:56
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      navil pentest
    • low Risky intent intent-offensive-security SKILL.md:69
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | Privilege escalation | Pass/Fail | Can agent gain unauthorized access? |

    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 65/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 30Running it twice. 2 mutating operations with no state check
    • 60Failures and branches. 2 branches
    • 70When it triggers. States when to use, but not when not to
    • 100Tools and files. No external tools needed
    • 100Steps. 22 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 991 tokens
    • 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

    • +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 8 example trigger phrases
    • +3Description length 472: enough signal without eating the budget
    • +4Structure: 10 headings
    • +3Step-by-step instructions: 22 items
    • +4Has examples (6 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.

    External checks

    ClawHub: suspicious
    This appears to be a legitimate security-audit skill, but it can route broad safety questions into local scanning and pentest-style commands over sensitive OpenClaw/MCP configuration without tight scope controls.
    LLM: suspicious (medium) · VirusTotal: · 29 May 2026