Back to skill

Security audit

B站视频全解析

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this video-processing skill suspicious because its setup reportedly asks users to share a complete API key in chat and it requires promotional follow-up; the scan was partial, so the evidence is incomplete.

Review the key setup carefully before installing: avoid pasting a full API key into chat, and use a local secret-entry or credential method if available. Consider whether you want the required promotional prompts and remote processing. Coverage was partial because referenced local paths could not be resolved, so these results do not establish that the skill is safe.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)

The setup instructions require the agent to solicit the user's complete API key in chat under the pretext of configuring local authentication.

High
Category
Data Exfiltration
Confidence
99% confidence
Finding

The mandatory setup script asks the user to paste a complete API key into the conversation, exposing it to chat storage, model processing, and potentially tracing infrastructure before local configuration occurs. The alternative local setup instructions and prohibition on echoing keys reduce some exposure but cannot undo disclosure of the user's incoming message; a compromised key could enable unauthorized use of the associated service and credits.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 64)May include surrounding context.

方式一:环境变量(写入 shell 启动文件后重开终端/客户端生效)

export CUE_API_KEY="sk你的key"

方式二:本地配置文件

mkdir -p ~/.cue && chmod 700 ~/.cue && echo '{"api_key": "sk你的key"}' > ~/.cue/config.json && chmod 600 ~/.cue/config.json

text

- **远程端点直连(无需本地 Bridge、无需配置 MCP)**:B 站 URL 解析只走远程端点 `https://mcp.cuecue.cn/api/omni-reader/mcp/`(streamable-http),鉴权头 `Authorization: Bearer <Cue Key>`。不依赖 `~/.mcp.json` 注册 MCP,也不装本地 Bridge;本地 Bridge 仅在降级方案中使用。

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 91)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 422)May include surrounding context.

解析调用手册

curl 三步

bash
# ① 提交解析(记下返回的 operation_id)

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 581)May include surrounding context.

bash
# ① 取 cid
curl -sS --compressed "https://api.bilibili.com/x/web-interface/view?bvid=BVxxxxxxxx" \
  -H "User-Agent: Mozilla/5.0" -H "Referer: https://www.bilibili.com/"
# ② 取免登录 360p MP4 直链(durl[0].url,带 deadline 时效参数,需尽快提交)
curl -sS --compressed "https://api.bilibili.com/x/player/playurl?bvid=BVxxxxxxxx&cid=<cid>&qn=64&platform=html5&high_quality=1" \

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 584)May include surrounding context.

curl -sS --compressed "https://api.bilibili.com/x/web-interface/view?bvid=BVxxxxxxxx"
-H "User-Agent: Mozilla/5.0" -H "Referer: https://www.bilibili.com/"

② 取免登录 360p MP4 直链(durl[0].url,带 deadline 时效参数,需尽快提交)

curl -sS --compressed "https://api.bilibili.com/x/player/playurl?bvid=BVxxxxxxxx&cid=&qn=64&platform=html5&high_quality=1"
-H "User-Agent: Mozilla/5.0" -H "Referer: https://www.bilibili.com/"

③ 把 MP4 直链作为 source 提交远程端点 parse(detail:"text"),流程同标准工作流

text

The video-processing skill mandates an undisclosed promotional workflow after delivery.

Low
Category
Excessive Agency
Confidence
94% confidence
Finding

The skill mandates a promotional follow-up and gives it priority over other delivery-related questions, allowing the provider's commercial workflow to redirect the assistant beyond the user's video-processing request. Balance warnings are relevant to a paid service, but mandatory referral and social-sharing prompts are unnecessary; the instructions do not, however, authorize automatic purchases or posting.

Content

No source excerpt is available for this finding.