ClawHub
Back to skill

Security audit

Scan To Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill decodes QR codes into ClawHub skill slugs and only performs installation after an explicit confirmation step.

Before installing from a QR code, check that the decoded slug is the skill you intended to install, especially for plain slugs or command-text QR payloads. Installation modifies your local ClawHub skill set, so only confirm skills from sources you trust.

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
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill instructs the agent to invoke local scripts and the ClawHub CLI to decode QR content and install a skill, but it declares no explicit tool scope or permission boundaries. Because the QR content can influence what gets installed and the workflow includes shell/network-capable operations, the absence of declared restrictions increases the chance of over-broad execution or unintended installs in environments that rely on metadata-based tool gating.

subprocess module call

Medium
Category
Dangerous Code Execution
Content
if not shutil.which("zbarimg"):
        return None
    try:
        p = subprocess.run(["zbarimg", "--quiet", "--raw", image_path], capture_output=True, text=True, check=True)
        out = p.stdout.strip()
        return out if out else None
    except Exception:
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
print("DRY RUN: pass --confirm to actually install. Requires user approval first.")
        sys.exit(0)

    p = subprocess.run(cmd)
    sys.exit(p.returncode)
Confidence
70% confidence
Finding
subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Static analysis

No suspicious patterns detected.