ClawHub
Back to skill

Security audit

gmp2025-transition

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow local countdown and checklist helper for a China medical-device GMP transition, with no hidden network, file, subprocess, persistence, or credential behavior found.

Before installing, treat the regulatory dates and checklist as planning aids only. The skill itself says its data is frozen and does not replace official NMPA or local regulator guidance, so compliance decisions should be checked against current official sources and qualified personnel.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The natural-language description is presented only in Chinese and does not mention any user choice, fallback, or opt-in for language/locale. This can violate language/locale policy expectations when a skill is consumed in broader environments where users may not have selected Chinese.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The manifest's read_when activation guidance is provided only in Chinese, which can force a specific language/locale for discovering or invoking the skill. Although the file includes English descriptions elsewhere, it does not explicitly offer a user language choice for these key trigger conditions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.