ClawHub
Back to skill

Security audit

A 股多空辩论

Security checks for vulnerabilities and agentic risk

Overview

This stock-analysis skill is mostly aligned with its purpose, but it asks the agent to run an unverified proxy binary from /tmp and stop processes by broad name matching.

Review before installing. Only use this skill if you trust and can verify the mihomo binary and config it expects under /tmp, are comfortable sending stock data and prompts to BigModel GLM, and can tolerate a local proxy process being started and stopped. Avoid shared servers unless proxy handling is changed to a verified binary, explicit user approval, exact PID tracking, and reliable cleanup.

SkillSpector

Vulnerability Patterns
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Session Persistence

Medium
Category
Rogue Agent
Content
# 启动代理（如未运行）
stock_start_proxy() {
    pgrep -f mihomo_bin > /dev/null && return
    nohup /tmp/mihomo_bin -f /tmp/mihomo_config.yaml -d /tmp/mihomo_data > /tmp/mihomo.log 2>&1 &
    sleep 2
    curl -s --connect-timeout 5 --proxy ${STOCK_PROXY:-http://127.0.0.1:7890} https://httpbin.org/ip | grep -q origin || echo "PROXY_DOWN"
}
Confidence
93% confidence
Finding
The skill starts a background proxy process with nohup and relies on later cleanup with pkill, which can leave a persistent network-modifying process running if execution is interrupted or cleanup is skipped. A lingering proxy can reroute later traffic, affect other workloads on the host, and expand exposure by changing network boundaries beyond the intended data-collection step.

Static analysis

No suspicious patterns detected.