ClawHub
Back to skill

Security audit

System Vigil

Security checks for vulnerabilities and agentic risk

Overview

This skill only performs a local system health readout, with minor documentation and metric accuracy issues but no hidden persistence, network activity, or destructive behavior.

Install this only if you are comfortable with the skill reading basic host resource information. Treat the CPU value as load average, not CPU percentage, and expect the actual JSON output to differ from the README example.

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
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • 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 (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill documentation instructs the agent to execute a Python script and explicitly depends on shell-accessed system binaries (`df`, `free`, `uptime`), but it does not declare any tool scope such as `permissions` or `allowed-tools`. This creates an authorization gap where an agent or runtime may invoke shell and file-read capabilities without an explicit least-privilege contract, increasing the risk of unintended command execution or broader host inspection than reviewers expect.

subprocess module call

Medium
Category
Dangerous Code Execution
Content
def get_disk_usage():
    try:
        # Check root partition
        out = subprocess.check_output(['df', '-h', '/']).decode('utf-8')
        # Extract percentage
        match = re.search(r'(\d+)%', out)
        if match:
Confidence
70% confidence
Finding
subprocess module calls execute external commands. Without careful input validation, this enables command injection.

subprocess module call

Medium
Category
Dangerous Code Execution
Content
def get_memory_usage():
    try:
        out = subprocess.check_output(['free', '-m']).decode('utf-8')
        lines = out.split('\n')
        mem_line = [l for l in lines if l.startswith('Mem:')][0]
        parts = mem_line.split()
Confidence
70% confidence
Finding
subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Description-Behavior Mismatch

Medium
Confidence
93% confidence
Finding
The manifest says the skill monitors Disk, RAM, and CPU health, but the implementation never measures CPU usage. Instead, it reads /proc/loadavg and returns the 15-minute load average, which is a different metric and not equivalent to CPU utilization. This creates a semantic mismatch between the advertised behavior and the actual output.

Static analysis

No suspicious patterns detected.