ClawHub
Back to skill

Security audit

using-agent-skills

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed workflow-routing guide with no executable code, persistence, credentials, or data exfiltration behavior.

Reviewers should be aware that this is a broad meta-skill for choosing other development workflow skills, so its usefulness depends on whether those referenced skills are actually installed and trusted. The file is Chinese-localized and partially mojibake-corrupted, which may make the guidance harder to audit, but no unsafe behavior was found in the inspected artifact.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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 (2)

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 1)May include surrounding context.

md
---
name: using-agent-skills
version: 1.0.0
description: "Check for applicable skills before responding to any task"

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The title and introductory description switch into Chinese and present the skill guidance in that language, with no statement that users may choose another language. This can violate a language/locale policy when the skill effectively constrains interaction language without opt-in or justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.