Back to skill

Security audit

抖音短视频全解析

Security checks for vulnerabilities and agentic risk

Overview

The skill is marked suspicious because its setup asks users to share a complete API key in chat, and the scan is partial, so some referenced material was not resolved.

Review the key setup and remote-service use before installing. Avoid sharing an API key in chat; configure it through a local secure method and rotate it if you have already shared it. The scan covered the reported Markdown component but was marked partial because some local references could not be resolved, so the evidence is incomplete.

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 onboarding script directs the agent to solicit a complete API key in conversation under the pretext of configuring it locally.

Medium
Category
Data Exfiltration
Confidence
97% confidence
Finding

The mandatory onboarding wording repeatedly directs the agent to solicit a complete credential, making insecure secret collection the default setup path. This overlaps the SQP-2 finding rather than establishing a separate theft mechanism: the service legitimately requires authentication, and the supplied content does not demonstrate malicious credential harvesting, but saving the key locally afterward does not make chat submission safe.

Content

No source excerpt is available for this finding.

The setup workflow requests the full API key in chat without warning about exposure through conversation storage or processing.

Medium
Category
Output Handling
Confidence
98% confidence
Finding

The setup instructions explicitly ask users to paste their complete API key into the conversation, exposing it to conversation storage and model-processing infrastructure before it is saved locally. Local configuration alternatives and prohibitions on echoing the key reduce subsequent exposure but do not undo disclosure through the initial message; a compromised key could enable unauthorized API usage and consume paid credits.

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":{}}' \

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 365)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)