T05 · Unauthorized Access and Privilege Escalation
- Location
SKILL.md:43- Finding
Claude Code Is Routinely Launched with Permission Checks Disabled
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This skill is meant to control Claude Code, but it repeatedly recommends running it with permission checks bypassed for code-changing tasks.
Review before installing. Use this only in isolated project directories or disposable worktrees, avoid bypassing permission checks for routine work, do not paste secrets or sensitive logs into prompts, and do not run the recursive chmod guidance unless you have identified the exact file that needs permission changes.
SKILL.md:43Claude Code Is Routinely Launched with Permission Checks Disabled
SKILL.md:219Recursive Permission Modification Grants Unnecessary Write Access Across the Project
This skill delegates tasks to an external model provider via the claude CLI, which can transmit user prompts, code context, and repository data outside the host system. In a code-control skill, that is materially relevant because users may paste secrets, proprietary code, or logs into prompts without any warning or minimization controls.
# 在当前目录运行
claude --permission-mode bypassPermissions --print "你的任务描述"
# 在指定项目目录运行
cd /path/to/project && claude --permission-mode bypassPermissions --print "你的任务描述"
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).
process action:list
git worktree remove /tmp/feature-a git worktree remove /tmp/feature-b
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).
git worktree remove /tmp/feature-a git worktree remove /tmp/feature-b
## 📝 常用命令模板
The code-development template sends substantial project instructions and likely source context to an external Claude CLI, creating a risk of unintentional disclosure of proprietary code or secrets embedded in task descriptions. Because the skill is specifically designed to automate development work, the chance of sharing sensitive internal context is elevated.
# 开发新功能
claude --permission-mode bypassPermissions --print "
开发一个用户登录功能,要求:
1. 使用 JWT 认证
2. 包含密码加密
The bug-fix template explicitly encourages pasting error logs and file paths into an external model invocation; logs often contain tokens, PII, stack traces, hostnames, or internal paths. Sending that material to a third-party CLI without screening can expose sensitive operational details.
"
# 修复 bug
claude --permission-mode bypassPermissions --print "
修复 issue #123 中的空指针异常。
错误日志:[粘贴错误信息]
相关代码:[文件路径]
The PR review template delegates repository diff analysis to an external provider, which may disclose proprietary source changes or security-sensitive code. While external model usage is part of the skill's purpose, the risk remains real because no consent, classification, or redaction controls are described.
# 审查 PR
claude --permission-mode bypassPermissions --print "
审查这个 PR 的改动:
1. 检查代码质量
2. 找出潜在 bug
The batch refactor template can expose broad swaths of a codebase to an external model service, increasing the likelihood of transmitting sensitive business logic or embedded secrets. The automation-oriented framing makes this more dangerous because users may run large-scale transformations without considering data handling implications.
# 批量重构
claude --permission-mode bypassPermissions --print "
将所有 .js 文件转换为 .ts:
1. 添加类型注解
2. 修复类型错误
The manifest description and main documentation are written entirely in Chinese and describe the skill as the dedicated interface for controlling Claude Code, without indicating that other languages are supported. This can violate a language/locale policy when a skill imposes a specific language without user opt-in or documented regional justification.
The skill claims it avoids 'full permissions' but standardizes on --permission-mode bypassPermissions, which explicitly disables permission checks for the external Claude CLI. In this context, that allows autonomous code changes and potentially destructive filesystem or repo actions without interactive approval, contradicting the stated safety model.
The document says sensitive operations require confirmation, but the provided command patterns invoke Claude in a mode that bypasses permission prompts and permit modification-oriented tasks such as refactoring, bug fixing, and feature development. This mismatch encourages operators to believe protections exist when the examples actually suppress them.