ClawHub
Back to skill

Security audit

finishing-a-development-branch

Security checks across malware telemetry and agentic risk

Overview

This skill guides a user-controlled git branch completion workflow and its sensitive actions are disclosed and gated by tests, menus, or explicit confirmation.

Before installing, understand that this skill is meant to help finish git branches and can guide an agent to merge locally, push a branch, create a PR, remove an owned worktree, or delete a branch. Those actions are part of the stated purpose, but you should only use it in repositories where you want the agent to help with branch integration decisions.

SkillSpector

By NVIDIA
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)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The manifest description contains broad natural-language trigger phrases like 'selesaikan branch ini' and 'tes lulus, mau merge?' that can match ordinary conversation outside a tightly scoped invocation flow. In an agent system that auto-selects skills from descriptions, this can cause the skill to activate unexpectedly and perform git-integrating actions in the wrong context, increasing the risk of unintended branch operations.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger engine states only that the skill activates when the user request 'matches the description above,' which delegates activation to an already broad description and leaves too much room for ambiguous matching. Because this skill can lead to merges, pushes, PR creation, and branch cleanup, ambiguous activation increases the chance of executing sensitive git workflows when the user was only discussing options rather than requesting action.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.