Back to skill

Security audit

Clawhub Mirror

Security checks for vulnerabilities and agentic risk

Overview

This skill is not clearly malicious, but it persistently redirects ClawHub installs to preferred mirror registries without enough trust verification or clear control.

Review this carefully before installing. It is intended to improve mirror access, but it can change where future ClawHub skills are fetched from. Only use it if you trust the listed mirror operators and ClawHub independently verifies package signatures or hashes. Prefer manual, session-only configuration over adding the loader to a shell profile.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (3)

T08 · Insecure Dependencies

Error
Location
scripts/configure_mirror.py:17
Finding

Automatic Redirection to Unverified Third-Party Package Mirrors

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/configure_mirror.py:151
Finding

Command Injection Through Unsafe Path Interpolation in Generated Shell Loader

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Note
Location
scripts/configure_mirror.py:184
Finding

Predictable Temporary Files Allow File Clobbering in Generated Windows Loader

Content
View full analysis
temp_site.txt set /p CLAWHUB_SITE= temp_reg.txt set /p CLAWHUB_REGISTRY=
Remediation
View remediation
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (8)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill instructs users to run PowerShell scripts, write persistent configuration files under the user profile, modify environment-dependent behavior, and contact multiple external mirror domains, yet the manifest does not declare any permissions or allowed tools. This creates a transparency and least-privilege problem: reviewers and users cannot easily assess or constrain the skill's network, shell, file-write, and environment-manipulation behavior, increasing the risk of unsafe execution or silent expansion of trust to unverified mirrors.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest description is written entirely in Chinese and describes the skill as prioritizing domestic Chinese mirrors, but it does not state that the skill is region-specific or offer any language/locale choice. Under the policy rules, forcing a specific language or locale without opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The module docstring and all user-facing messages are written in Chinese, which effectively constrains the skill to a specific language. The file does not offer an opt-in language choice or explain that the tool is intentionally region-specific, so this is a natural-language locale policy concern.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill performs an unnecessary execution of the external clawhub CLI after configuration, expanding the trust boundary from simple file/network configuration into arbitrary local code execution of whatever clawhub resolves to on the host PATH. In an agent/skill context, this is dangerous because a malicious or trojanized clawhub binary, wrapper script, or PATH hijack could be triggered merely by running a mirror-setup tool.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The module docstring is entirely in Chinese and includes operational guidance, but the file provides no language choice or opt-in for users who may expect another language. This matches the policy category for language/locale constraints because the skill presents user-facing instructions in a fixed language without documenting that limitation or offering alternatives.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest describes a mirror-source management skill that selects the best mirror and configures access. Invoking subprocess.run(['clawhub', 'list'], ...) adds process-execution capability beyond straightforward mirror testing and configuration, and that capability is not justified by the stated purpose itself.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/configure_mirror.py (reported line 270)May include surrounding context.

python
print("\n测试clawhub命令...")
    try:
        import subprocess
        result = subprocess.run(['clawhub', 'list'], capture_output=True, text=True)
        if result.returncode == 0:
            print("测试成功!")
        else:

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/simple_configure.py (reported line 113)May include surrounding context.

python
print("\n测试clawhub命令...")
    try:
        import subprocess
        result = subprocess.run(['clawhub', 'list'], capture_output=True, text=True)
        if result.returncode == 0:
            print("测试成功!")
        else: