ClawHub
Back to skill

Security audit

Finishing Branch

Security checks for vulnerabilities and agentic risk

Overview

This skill provides a user-directed Git branch finishing workflow; its branch merge, push, PR, and deletion actions are disclosed and controlled, though users should note that the runtime prompts are in Chinese.

Install only if you are comfortable with a Chinese-language Git workflow. Before choosing merge, push, PR creation, or discard, make sure you understand the prompt and confirm the target base branch and feature branch; the discard path can permanently delete the local feature branch after confirmation.

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 (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill content is written entirely in Chinese and directs specific user-facing prompts without offering any language negotiation or opt-in. In a multi-user or multilingual environment, this can cause users to misunderstand destructive or workflow-critical choices such as merge, PR creation, or branch deletion, increasing the risk of accidental actions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.