skill-trust-auditor

Name: skill-trust-auditor
Author: InternLM

Security Verified v1.1.3

Repo stars 402
Author updated Live
Author repo WildClawBench

Fluxly profile Facts only: domain, agents, trust score, runtime, permissions and network

Domain: Security
Compatible agents: Claude Code
Cursor
Cline
Codex
Windsurf
Gemini CLI

+20
Trust score: 92 / 100 · audit passed
Author / version / license: @InternLM · v1.1.3 · no license declared
Token usage: Lean
Setup complexity: Guided setup
External API key: Not required
Operating systems: Unspecified (assume cross-platform)
Runtime requirements: No special requirements
Permissions: Read-only
Write / modify
Shell exec
Env read
Network behavior: External requests
Install commands: 26 variants

Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.

Heads up: 未限定 allowed-tools，默认拥有全部工具权限。

Output preview skill-trust-auditor.preview

---
name: skill-trust-auditor
description: Audit a ClawHub skill for security risks BEFORE installation. Audit any ClawHub skill for securi…
category: security
runtime: no special runtime
---

# skill-trust-auditor output preview

## PART A: Task fit
- Use case: Audit a ClawHub skill for security risks BEFORE installation. Audit any ClawHub skill for security risks before installation. Tell OpenClaw: "Install the skill-trust-auditor skill." The agent will handle the installation and configuration automatically. makes outbound network calls. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “🛠️ Installation / 1. Ask OpenClaw (Recommended) / 2. Manual Installation (CLI)” and do not present inference as author intent.

## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Audit a ClawHub skill for security risks BEFORE installation. Audit any ClawHub skill for security risks before installation. Tell OpenClaw: "Install the skill-trust-auditor skill." The agent will handle the installation and configuration automatically. makes outbound network calls. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “🛠️ Installation / 1. Ask OpenClaw (Recommended) / 2. Manual Installation (CLI)” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files, run shell commands, read environment variables; may access external network resources; usually needs no extra API key.

## Running Rules
- read files, write/modify files, run shell commands, read environment variables; may access external network resources; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options.

SKILL.md SKILL.md

---
name: skill-trust-auditor
description: Audit a ClawHub skill for security risks BEFORE installation. Audit any ClawHub skill for securi…
category: security
source: InternLM/WildClawBench
---

# skill-trust-auditor

## When to use
- Audit a ClawHub skill for security risks BEFORE installation. Audit any ClawHub skill for security risks before instal…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.

## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.

## Execution rules
- Organize steps around “🛠️ Installation / 1. Ask OpenClaw (Recommended) / 2. Manual Installation (CLI)” and keep inference separate from source facts.
- read files, write/modify files, run shell commands, read environment variables; may access external network resources; usually needs no extra API key.
- Validate with a small sample before expanding the task.

## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies.

Evidence boundary and execution chain

The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.

skill "skill-trust-auditor" {
  input      -> user goal + target files + boundaries + acceptance criteria
  context    -> 🛠️ Installation / 1. Ask OpenClaw (Recommended) / 2. Manual Installation (CLI)
  rules      -> SKILL.md triggers / order / output contract
  runtime    -> no special runtime | read files, write/modify files, run shell commands, read environment variables | may access external network resources
  guardrails -> usually needs no extra API key + small-sample validation + diff/log review
  output     -> copyable result + checklist + next iteration
}

Interpretation is structured for decision-making; original keeps the upstream SKILL.md unchanged.

Decide Fit First

Core job: Audit a ClawHub skill for security risks BEFORE installation. Audit any ClawHub skill for security risks before installation. Te…
Best fit: Use it when the task has reusable inputs, steps, and validation criteria rather than a one-off answer.
Avoid forcing it: If the source lacks commands, platform support, or external-service evidence, keep those fields unknown instead of guessing.

Design Intent

Structure: The skill is organized around “🛠️ Installation”, “1. Ask OpenClaw (Recommended)”, “2. Manual Installation (CLI)”, “Setup (first run only)”, showing how the author expects the agent to judge fit, collect context, and produce verifiable output.
Trigger evidence: Prioritize the author’s wording around when to use it, what context to collect, and what output shape to produce.
Evidence boundary: Author text states facts, repository files prove commands and paths, and Fluxly only adds fit, limits, and usage judgment.

How To Use It

Inputs: Provide target material, scope, expected result, forbidden changes, and validation method.
Invocation: Name skill-trust-auditor directly; if the source includes slash commands, start with the command and then add task context.
Validation: Start small and check whether the result follows “🛠️ Installation / 1. Ask OpenClaw (Recommended) / 2. Manual Installation (CLI)” before expanding.

Boundaries And Review

Dependencies: It usually needs no extra API key, so start with a small validation task.
Permissions: Declared permissions include read / write / shell-exec / env-read; ask the agent to state file, command, and rollback boundaries before acting.
Quality bar: A useful result names the deliverable, evidence, and next action. Generic prose means the task needs tighter context.

Skill Trust Auditor

Audit any ClawHub skill for security risks before installation.

🛠️ Installation

1. Ask OpenClaw (Recommended)

Tell OpenClaw: "Install the skill-trust-auditor skill." The agent will handle the installation and configuration automatically.

2. Manual Installation (CLI)

If you prefer the terminal, run:

clawhub install skill-trust-auditor

Setup (first run only)

bash scripts/setup.sh

Audit a Skill

When user says "audit [skill-name]" or "is [skill-name] safe" or before any clawhub install:

bash scripts/audit.sh [skill-name-or-url]
# Example:
bash scripts/audit.sh steipete/clawhub
bash scripts/audit.sh https://clawhub.ai/someuser/someskill

Output:

{
  "skill": "someuser/someskill",
  "trust_score": 72,
  "verdict": "INSTALL WITH CAUTION",
  "risks": [
    {"level": "HIGH", "pattern": "curl to external domain", "location": "scripts/sync.sh:14"},
    {"level": "MEDIUM", "pattern": "reads MEMORY.md", "location": "SKILL.md:23"}
  ],
  "safe_patterns": ["no env var access", "no self-modification"],
  "author_verified": false,
  "recommendation": "Review scripts/sync.sh:14 before installing. The external curl call could exfiltrate data."
}

Post to user with clear summary:

🛡️ Trust Audit: someuser/someskill
Score: 72/100 — ⚠️ INSTALL WITH CAUTION

🔴 HIGH: curl to unknown domain in scripts/sync.sh:14
🟡 MEDIUM: reads your MEMORY.md

Recommendation: Inspect line 14 of sync.sh before proceeding.
Run: clawhub show someuser/someskill --file scripts/sync.sh

Trust Score Guide

Score	Verdict	Action
90-100	✅ SAFE	Install freely
70-89	⚠️ CAUTION	Review flagged items first
50-69	🟠 RISKY	Only if you understand the risks
0-49	🔴 DO NOT INSTALL	High probability of malicious intent

Risk Pattern Reference

HIGH RISK (-30 each):

process.env access in scripts
curl/wget to non-standard domains
Reading ~/.config or ~/.openclaw directly
exec() with user-controlled input
Instructions to modify SOUL.md/AGENTS.md/openclaw.json

MEDIUM RISK (-10 each):

Any outbound API calls (even to known services)
File writes outside workspace
Reading MEMORY.md or diary files

LOW RISK (-3 each):

web_fetch to standard domains
Read-only file access in workspace

Auto-Audit Mode

Optionally prepend audit to every install:

# Add to your shell aliases:
alias clawhub-safe='bash ~/.openclaw/workspace/skills/skill-trust-auditor/scripts/audit.sh $1 && clawhub install $1'

ClawHavoc Pattern Reference

See references/clawhavoc-patterns.md for known malicious patterns from the February 2026 incident. Update this file when new incidents are reported.

Install command

One-click installPick a runner, click Copy, paste into your terminal, press enter

npx skills add InternLM/WildClawBench/skills/6/skill-trust-auditor -y

Open general install guide

View skill source

Works with

Claude Code
Cursor
Cline
Codex
Windsurf
Gemini
OpenCode
Roo Code
AAide
+Augment
GitHub Copilot
OpenClaw
KKiro
Junie
WWarp
Goose
Trae
Kilo Code
OpenHands
Amp
Zencoder
CContinue
AIAider
CodeBuddy
CodeGeeX
Replit Agent

Security audit

92 / 100

Verified

未声明 license/许可。
未限定 allowed-tools，默认拥有全部工具权限。

Metadata

Source: github
InternLM/WildClawBench
Version: 1.1.3
中文

Category & tags

Category Security