SKILLEMALL.ai
GitHub ↗ RU Sign in

AC navil-shield

Runtime security for OpenClaw. Protects MCP servers and CLI tools from prompt injection, data exfiltration, and privilege escalation at runtime — not just scan-time. Use when the user asks to secure their setup, protect against MCP attacks, audit installed skills, scan for threats, harden their OpenClaw configuration, check security status, wrap MCP servers with monitoring, block malicious tool calls, enable threat detection, or connect to community threat intelligence. Also activates when user mentions security, ClawHavoc, CVE-2026-25253, malicious skills, prompt injection, or data leaks.

ClawHub Agent Skills author: ivanpantheon v1.0.2 MIT-0 4 files body ≈ 1 720 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 64/100 · Has gaps — weak spots: result and completion, inputs and preconditions

AnalyzerAI and agentstype 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
91/100
safety, quality, tests
Safety 60%
96
Quality 40%
84
Run on models
none yet
Process rating
C
64/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Tools and files w 18
60
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 · 4

    ✓ No critical or high findings

    Medium and low: 4
    • low Risky intent intent-offensive-security skill-card.md:2
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
      Navil Shield helps protect OpenClaw MCP servers and CLI tools at runtime from prompt injection, data exfiltration, and privilege escalation. <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: Runtime security for OpenClaw. Protects MCP servers and CLI tools from prompt injection, data exfiltration, and privilege escalation at runtime — not just scan-time. Use when the user ask
      detector
    • low Risky intent intent-offensive-security SKILL.md:142
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      Run the penetration test suite:
    • low Risky intent intent-offensive-security SKILL.md:145
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      navil pentest

    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 64/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 100Steps. 35 steps
    • 100Failures and branches. 3 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1720 tokens
    • 100Running it twice. No mutating operations
    • 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

    • +5Description has no quoted example phrases that should trigger the skill
    • +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
    • +3Description length 596: enough signal without eating the budget
    • +4Structure: 20 headings
    • +3Step-by-step instructions: 35 items
    • +4Has examples (12 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.

    External checks

    ClawHub: suspicious
    Navil Shield appears purpose-aligned as a runtime MCP security proxy, but it needs review because it can install an external package, persistently wrap MCP servers, auto-run on broad triggers, and shares telemetry by default.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026