ClawHub
Back to skill

Security audit

Capa Management

Security checks for vulnerabilities and agentic risk

Overview

This skill is a CAPA quality-management report assistant with no evidence of hidden data access, persistence, or destructive behavior.

Installers should expect a Chinese CAPA report-writing assistant that may enforce a fixed workflow and Chinese output. Confirm the desired output directory before generating files, and be aware that referenced helper resources are not included in the inspected artifact.

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 (1)

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The skill explicitly enforces Chinese-only output ('全中文文档'), which can override user language preferences and reduce accessibility or usability for operators, auditors, or downstream systems expecting another language. While not a code-execution or data-exfiltration issue, it is a genuine policy/usability vulnerability because rigid output-language constraints can cause misunderstandings, failed handoffs, or compliance friction in multilingual environments.

Static analysis

No suspicious patterns detected.