Back to skill

Security audit

Denote TOP ADS

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with medium confidence: one scanner reported no findings, while another flagged three behaviors that the verdict treats as expected or limited concerns in context.

The verdict is benign, but not risk-free. Before installing, consider that the skill makes authenticated network requests and does not declare its tool scope. The scan reports complete component coverage, though image files were outside some static analyzers’ scope.

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
Vulnerability Patterns
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • 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
Findings (3)

Tainted flow: 'request' from os.environ.get (line 69, credential/environment) → urllib.request.build_opener.open (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/top_ads.py (reported line 71)May include surrounding context.

python
url = ORIGINS[args.environment] + API_PATH + args.command + '?' + urlencode(query)
    request = Request(url, headers={'Authorization': f'Bearer {key}', 'Accept': 'application/json'})
    try:
        with build_opener(NoRedirect()).open(request, timeout=90) as response:
            data = json.load(response)
    except HTTPError as exc:
        # Decode user-facing structured errors from the service. Avoid printing a proxy error page.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, file_read, network, shell.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · report.py (reported line 22)May include surrounding context.

python
def call(*arguments):
    result = subprocess.run([sys.executable, str(ROOT / "scripts/top_ads.py"), *arguments],
                            capture_output=True, text=True)
    if not result.returncode:
        return json.loads(result.stdout)["data"], None