ClawHub
Back to skill

Security audit

skillguard

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed remote security-audit helper that sends user-selected skill materials to an external audit service, with scoped inputs and redaction guidance.

Before installing, confirm you are comfortable using a hosted audit service and storing SKILLGUARD_API_KEY in OpenClaw configuration. Only submit skill files you intend to have audited, redact secrets and personal or proprietary data first, and be aware that the documentation is currently Chinese-only.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (6)

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The file's user-facing description and instructions are entirely in Chinese, including the manifest description and installation steps. This forces a specific language for users without any opt-in or justification, which matches the policy category for language or locale constraints.

Natural-Language Policy Violations

Medium
Confidence
86% confidence
Finding
The file’s natural-language instructions are entirely in Chinese, including the key handling guidance and configuration description. Under the policy, forcing a specific language without user opt-in or a documented justification is a natural-language policy violation.

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
This markdown file presents all operational instructions exclusively in Chinese, and it does not indicate that the skill is region-specific or provide an opt-in for language preference. Under the policy, forcing a specific language without user choice is a natural-language policy violation.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
API_ROOT="${AI_SKILLS_API_URL:-https://ai-skills.open-idea.net}/api/v1"

curl --fail-with-body "$API_ROOT/skillguard/audit" \
  -H "Authorization: Bearer $SKILLGUARD_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: audit-uuid-001" \
Confidence
84% confidence
Finding
The documented curl example performs external transmission of skill content and attached files to a remote endpoint. In this skill context, that is expected behavior, but it is still security-relevant because audit inputs may contain sensitive prompts, code, internal URLs, or secrets, and the document does not clearly constrain or warn about that data flow.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The example shows sending full skill content and files to a third-party audit API using a bearer token, but it does not warn users that proprietary prompts, embedded secrets, or personal data may be transmitted off-host. In a security-audit skill, this omission is more significant because users may paste sensitive SKILL.md content and assume the tool is safe by default.

Natural-Language Policy Violations

Low
Confidence
82% confidence
Finding
All user-facing natural-language documentation in this file is presented in Chinese, with no indication that other languages are supported or that Chinese is required for a region-specific purpose. This can violate a language/locale policy when a specific language is imposed without user opt-in or documented justification.

Static analysis

No suspicious patterns detected.