Back to skill

Security audit

Git Worktree

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward git-worktree workflow guide that keeps activity scoped to the current worktree and avoids destructive Git commands unless the user explicitly asks.

Install this if you want Codex to follow a disciplined Git worktree workflow. Be aware that it allows user-directed code changes and commits in the current branch, so review the plan and git status before approving work.

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
Vulnerability Patterns
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • 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
Findings (2)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
65% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 75)May include surrounding context.

md
| 当前目录开发当前需求 | 切换其他 worktree 目录 |
| 当前分支提交代码 | 修改其他需求代码 |
| 分析当前目录代码 | 操作其他仓库/分支 |
| 从目录名解析归属 | `git reset --hard` / `clean -fd`(除非要求) |

---

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The description says the skill triggers when the user is in a worktree directory, mentions 'worktree', or mentions parallel multi-task development. Phrases like '提到 worktree' are broad natural-language triggers without clear exclusion conditions or a precise invocation list, which could overlap with ordinary discussion rather than an explicit request to use the skill.

Content

No source excerpt is available for this finding.