Back to skill

Security audit

抖音上升热点(抖音热点趋势选题助手-爆款选题)

Security checks for vulnerabilities and agentic risk

Overview

The skill performs a narrowly scoped Douyin trend lookup through the disclosed AI Skills service, with no material security concern found.

Use a dedicated AI Skills API key and check service charges. Your search terms and filters are sent to that provider. Review any separately supplied installation command before running it. All bundled files were inspected; live API behavior and external installer code were not verified.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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: 'req' from os.getenv (line 154, 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/run.py (reported line 161)May include surrounding context.

python
headers=build_headers(),
    )
    try:
        with OPENER.open(req, timeout=REQUEST_TIMEOUT_SECONDS) 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.

The setup instructions require a fixed Chinese response and explicitly prohibit translation without offering a language choice.

Medium
Category
Output Handling
Confidence
99% confidence
Finding

When the API key is missing or the user asks about installation or configuration, the skill mandates verbatim Chinese text and forbids translation. This imposes a response language without user opt-in; the Douyin-specific context does not justify preventing localized setup guidance.

Content

No source excerpt is available for this finding.