T05 · Unauthorized Access and Privilege Escalation
- Location
SKILL.md:26- Finding
Excessive File-System and Command-Execution Permissions
- Content
View full analysis
Vulnerability Details
File Location:
SKILL.md:26-29
Vulnerability Type: Excessive tool permissions and violation of least privilege
Risk Level: MediumVulnerable Code
yaml tools: - read - exec - writeRelated capability claims at
SKILL.md:186-190:markdown ## 主要功能 - **自动化执行**: 豆包大模型对话(免费 - **文件处理**: 支持多种文件格式的读取、解析和写入操作 - **API集成**: 通过标准化接口调用外部服务并处理响应 - **命令执行**: 在安全沙箱中执行系统命令并收集结果 - **信息检索**: 快速搜索和过滤目标数据Technical Analysis
The skill is presented primarily as a Doubao model conversation and search integration, but it requests general-purpose
read,write, andexectools. Ordinary remote model interaction does not inherently require unrestricted local file access or system command execution.No implementation, enforceable sandbox policy, command allowlist, file-path restriction, input validation mechanism, or confirmation boundary is included in the audited package. The statement that commands run in a secure sandbox is therefore a documentation claim rather than an enforceable control visible in the project.
If the hosting agent grants these tools directly, attacker-controlled conversation content could influence tool selection and arguments. This creates a confused-deputy risk in which a chat-oriented skill receives capabilities beyond those reasonably necessary for its stated function.
Attack Path
- A user or external content supplies a crafted chat instruction to the skill.
- The agent loads the skill and grants its declared
read,write, andexeccapabilities. - The crafted content persuades or causes the agent to invoke one of those tools as part of the requested conversation or automation workflow.
- The agent reads a local file, modifies a writable file, or executes a system command using its own runtime privileges.
- The resulting data or command output may be returned to the requester, while file changes or command side effects occur within the agent's accessible environment.
The pack ...[truncated 941 chars]
- Remediation
View remediation
Remediation Suggestions
- Remove
read,write, andexecunless each capability is strictly necessary for a documented use case. - Replace general-purpose tools with a narrowly scoped HTTPS API client restricted to approved Doubao endpoints, methods, and request schemas.
- If local file access is required:
- Restrict access to a dedicated working directory.
- Deny traversal, symbolic-link escapes, and absolute paths.
- Use separate read-only and narrowly scoped write permissions.
- Require explicit user confirmation before accessing sensitive files.
- If command execution is essential:
- Use a hardened sandbox with no host file-system or credential access.
- Permit fixed executable paths and structured arguments only.
- Prohibit shell interpretation and concatenation of user-controlled input.
- Apply resource, network, environment-variable, and execution-time limits.
- Require explicit confirmation for commands with side effects.
- Treat conversation content, retrieved text, and model output as untrusted data rather than executable instructions.
- Document the exact reason each capability is required and test that the skill fails closed when a request exceeds its authorization boundary.
- Remove
