ClawHub
Back to skill

Security audit

Raspberry Pi Serial Rescue / 树莓派串口急救

Security checks for vulnerabilities and agentic risk

Overview

This skill is a scoped Raspberry Pi serial-diagnostics helper that clearly gates installation, port access, and writes behind separate user approval.

Before installing, confirm you trust the JishuBuddy npm package and approve the exact displayed version. Treat installation, launching JishuBuddy, opening a serial port, serial writes, and any device-permission changes as separate decisions. Disable JishuBuddy telemetry before launch if you do not want activation or heartbeat telemetry.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • 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
Findings (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding
The skill’s declared purpose focuses on reading Raspberry Pi serial boot logs, but the instructions also authorize package preflight checks and global installation of JishuBuddy via npm. That expands the operational scope from passive diagnostics into host software management and network/package-supply-chain activity, which can surprise operators and increase attack surface if not clearly disclosed in the top-level description.

Tool Parameter Abuse

High
Category
Tool Misuse
Content
4. If permissions block access, explain the actual requirement and obtain
   approval before changing groups or permissions. On Linux, add the user
   only to the group actually required by that device. Do not use `chmod 666`
   or run the agent as root to bypass access controls.
5. Match the configured baud exactly. Garbled output commonly indicates a baud
   mismatch, framing mismatch, electrical problem, or incorrect signal path.
Confidence
80% 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).

Ae1

High
Category
analysis-evasion
Content
`<skill-directory>` to the absolute directory containing this `SKILL.md`,
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected

Sudo/Root Execution

Medium
Category
Privilege Escalation
Content
4. If permissions block access, explain the actual requirement and obtain
   approval before changing groups or permissions. On Linux, add the user
   only to the group actually required by that device. Do not use `chmod 666`
   or run the agent as root to bypass access controls.
5. Match the configured baud exactly. Garbled output commonly indicates a baud
   mismatch, framing mismatch, electrical problem, or incorrect signal path.
Confidence
80% confidence
Finding
Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Static analysis

No suspicious patterns detected.