Back to skill

Security audit

抖音热点排行榜(抖音热点选题助手)

Security checks for vulnerabilities and agentic risk

Overview

The skill retrieves Douyin trends through a disclosed API, with no material security concern supported by the inspected files.

Use an AI Skills key you control and check usage charges. Your key and tenant ID go to ai-skills.ai; topic filtering stays local. Review any separate installer before running it. External installer code and server-side processing are outside this artifact review.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (4)

Tainted flow: 'req' from os.getenv (line 174, 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 181)May include surrounding context.

python
headers=build_headers(),
    )
    try:
        with OPENER.open(req, timeout=timeout) as response:
            raw = response.read().decode("utf-8")
            try:
                result = json.loads(raw)

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.

Setup instructions mandate Chinese output without allowing the user's language preference.

Medium
Category
Output Handling
Confidence
99% confidence
Finding

When credentials are missing or the user asks about installation or configuration, the skill requires the Chinese text to be reproduced verbatim and explicitly prohibits translation. This imposes a response language without user opt-in or a documented justification for the restriction.

Content

No source excerpt is available for this finding.

The invocation question “现在最热门的是什么?” (“What is most popular right now?”) does not specify Douyin and could match general requests about news, products, or trends.

Low
Category
Trigger Abuse
Confidence
90% confidence
Finding

The question is broader than this skill's Douyin-specific hotlist function. Although the skill name identifies Douyin, the invocation wording contains no platform constraint or exclusion, creating ambiguity about when this skill should activate.

Content

No source excerpt is available for this finding.