ClawHub
Back to skill

Security audit

Daily Hotspot Push

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently creates scheduled QQ news briefings and stores the needed subscription settings, with no evidence of hidden or unrelated behavior.

Install this only if you want recurring news messages through your OpenClaw and QQBot setup. Review created cron jobs, remove subscriptions you no longer want, and avoid sensitive topics or destination identifiers if you do not want them stored locally or used by the delivery channel.

SkillSpector

Vulnerability Patterns
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

subprocess module call

Medium
Category
Dangerous Code Execution
Content
]
    for candidate in candidates:
        try:
            result = subprocess.run([candidate, "--version"], capture_output=True, text=True, encoding="utf-8", errors="replace")
            if result.returncode == 0 or result.stdout or result.stderr:
                return candidate
        except FileNotFoundError:
Confidence
84% confidence
Finding
The code resolves openclaw.cmd by searching PATH and accepts any executable that produces output for --version, even if it exits nonzero. In an attacker-controlled environment, a malicious binary earlier in PATH could be selected and then later executed with user-influenced arguments, leading to arbitrary code execution under the skill's privileges.

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill invokes shell commands, reads and writes local files, and creates persistent cron jobs, but it declares no permissions or trust boundary to the user. In a skill that accepts user-provided fields like target, time, timezone, and topics and passes them into command examples, this lack of explicit permissioning and capability disclosure increases the risk of unsafe command execution, unauthorized file modification, or persistent task creation without adequate review.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill creates real scheduled tasks and stores subscription and timezone data persistently, but the description does not require an explicit user warning or confirmation that automation and data retention will occur. This can lead to surprise background actions, unwanted recurring messages, and privacy issues from retaining identifiers and timezone preferences beyond the current interaction.

Static analysis

No suspicious patterns detected.