ClawHub
Back to skill

Security audit

lis-skill-bus 本地 Skill 联动总线（MCP 安装器）

Security checks for vulnerabilities and agentic risk

Overview

The skill’s local CAD data-sharing service, installation steps, and optional MCP registration match its disclosed purpose.

Preview installation with --dry-run and use SKIP_MCP_REG=1 if you only want the files copied. Protect shared CAD state and configuration backups. Uninstalling removes MCP registration but leaves installed files and saved project data. Review separately installed CAD skills used by the integration wrappers.

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
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding

The supplied command selects uninstall mode, reversing the declared installation workflow rather than showing a supporting installation detail. The script itself is not supplied, so specific deletions, resource accesses, and other effects cannot be verified.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, file_read, file_write, shell.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Tainted flow: 'b' from os.environ.get (line 43, credential/environment) → open (file write)

Medium
Category
Data Flow
Confidence
65% confidence
Finding

Data from a source is assigned to a variable that is later passed to a sink, creating a variable-mediated taint flow.

Content

Scanner excerpt · install_py.py (reported line 45)May include surrounding context.

python
# 保留既有内容：先备份一份，再向原文件追加新段
    b = str(cfg) + ".skillbus." + datetime.datetime.now().strftime("%Y%m%d%H%M%S") + ".bak"
    if cfg.exists():
        open(b, "wb").write(cfg.read_bytes())
        print(f"已备份原配置 -> {b}")
    command = str(Path(bus) / "skillbus.py").replace("\\", "\\\\").replace('"', '\\"')
    block = "\n" + sec + '\ntype = "stdio"\ncommand = "' + command + '"\nargs = ["serve"]\n'

Static analysis

No suspicious patterns detected.