ClawHub
Back to skill

Security audit

抖音实时上升热点榜｜排名变化与选题趋势

Security checks for vulnerabilities and agentic risk

Overview

The skill fits its trend-search purpose, but its network handling can expose your API key to an unintended server.

Before supplying a real API key, require HTTPS destination validation and redirect handling that prevents credentials from reaching another origin. Keeping the default URL alone does not address redirect leakage. Your query parameters go to AI Skills, and calls may consume account balance. Live service behavior and billing were not tested.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Tainted flow: 'req' from os.getenv (line 86, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
93% confidence
Finding

Sending the API key to the documented HTTPS service is legitimate authentication, not inherently exfiltration. However, the runner attaches that key to an unvalidated environment-configured destination, permits HTTP, and uses default redirect handling that can forward the custom X-API-Key header across origins. An attacker who can influence the base URL or induce a redirect could therefore obtain the credential; the supplied content does not establish an active malicious destination.

Content

Scanner excerpt · scripts/run.py (reported line 93)May include surrounding context.

python
headers=build_headers(),
    )
    try:
        with urllib.request.urlopen(req, context=SSL_CONTEXT) as response:
            return json.loads(response.read().decode("utf-8"))
    except urllib.error.HTTPError as exc:
        print_http_error(exc)

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

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.

Static analysis

No suspicious patterns detected.