ClawHub
Back to skill

Security audit

finishing-a-development-branch

Security checks for vulnerabilities and agentic risk

Overview

This skill gives a cautious, user-controlled workflow for finishing a Git development branch, with branch cleanup and push/merge actions disclosed and gated by user choice.

Install this only if you want the agent to help with Git branch completion tasks such as merging, pushing, creating PRs, and cleaning up worktrees. Review the options before approving them, especially branch deletion or worktree removal, because those are legitimate but high-impact Git operations.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (1)

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The declared description centers on finishing a development branch by taking one of several completion actions and safely handling worktree cleanup. The code instead performs only a pre-merge safety checklist. While some supporting pieces align (test checking and worktree visibility), the primary purpose is materially different: it is informational and blocking, not an action-taking branch-finalization tool. It also introduces secret scanning, which is not mentioned in the description. Therefore the description does not accurately represent the code's actual behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.