T08 · Insecure Dependencies
- Location
scripts/configure_mirror.py:17- Finding
Automatic Redirection to Unverified Third-Party Package Mirrors
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
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.
scripts/configure_mirror.py:17Automatic Redirection to Unverified Third-Party Package Mirrors
scripts/configure_mirror.py:151Command Injection Through Unsafe Path Interpolation in Generated Shell Loader
scripts/configure_mirror.py:184Predictable Temporary Files Allow File Clobbering in Generated Windows Loader
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.
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.
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.
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.
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.
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.
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
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 calls execute external commands. Without careful input validation, this enables command injection.
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: