Back to skill

Security audit

抖音短视频全解析

Security checks for vulnerabilities and agentic risk

Overview

The video-processing workflow is coherent, but its setup repeatedly asks users to expose a reusable API key in chat.

Use the documented local configuration option instead of pasting your key into chat, and restrict credential-file permissions to your account. Rotate any key already shared in a conversation. Submitted video links go to Cue and parsing consumes credits; the server's retention promise was not independently verified. Review is warranted for credential handling, while the inspected artifacts do not establish malicious intent.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

The setup instructions require users to disclose their complete API key in the conversation under the pretext of configuring local authentication.

High
Category
Data Exfiltration
Confidence
99% confidence
Finding

The onboarding instructions repeatedly direct users to paste their complete API key into the conversation, exposing a reusable credential to chat storage, model processing, and potentially transcript readers or logging integrations. Although an alternative local setup is offered and the skill prohibits echoing keys, neither safeguard removes the exposure created by soliciting the secret in chat; misuse could consume credits or access whatever capabilities the key authorizes.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 92)May include surrounding context.

md
CUE_KEY=$(python3 -c "import json,os;p=os.path.expanduser('~/.cue/config.json');print(json.load(open(p)).get('api_key','') if os.path.exists(p) else '')" 2>/dev/null || true)
CUE_KEY=${CUE_KEY:-$CUE_API_KEY}
echo "=== 1/4 API Key ===" && { [ -n "$CUE_KEY" ] && echo "已配置" || echo "未配置!"; }
echo "=== 2/4 远程端点 ===" && curl -sS --max-time 10 -X POST "https://mcp.cuecue.cn/api/omni-reader/mcp/" \
  -H "Authorization: Bearer $CUE_KEY" \
  -H "Content-Type: application/json" -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}' \

Mandatory verbatim Chinese prompts impose an output language without user opt-in.

Medium
Category
Output Handling
Confidence
98% confidence
Finding

The skill requires the credit-replenishment question and options to be used verbatim and prohibits changes, forcing Chinese user-facing output regardless of the user's preferred language. No language choice or justification for this restriction is provided; targeting Douyin does not inherently require Chinese interface text.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 364)May include surrounding context.

解析调用手册

curl 三步

bash
# 0)先从分享文案提取短链,并用浏览器 UA 展开为真实地址(关键!v.douyin.com 直连会 PARSE_FAILED)