Back to skill

Security audit

小红薯短视频全解析

Security checks for vulnerabilities and agentic risk

Overview

The skill is rated suspicious because scanners report instructions to ask for a full API key in chat and to require referral or purchase promotion; the scan was partial, so evidence is incomplete.

Consider avoiding installation unless you trust the Cue service and are comfortable with the reported credential and promotional instructions. Do not paste a complete API key into chat; use a secure local configuration method. Skillspector inspected the one listed component but marked analysis partial because several local references could not be resolved, so the evidence does not cover everything those references might involve.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Mandatory onboarding language directs the agent to solicit the user's complete API key in chat, presenting credential disclosure as a required setup step.

Medium
Category
Data Exfiltration
Confidence
99% confidence
Finding

The mandatory onboarding script repeatedly asks the user to paste a complete API key into chat, unnecessarily exposing a reusable credential to conversation storage and any systems or people with access to it. Local configuration alternatives and instructions not to echo the key reduce some exposure, but cannot undo its initial inclusion in the conversation; a leaked key could enable unauthorized service usage and credit consumption.

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 78)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 333)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)

The skill mandates referral and purchase promotion beyond its video-analysis and creation purpose.

Low
Category
Excessive Agency
Confidence
94% confidence
Finding

The manifest describes video parsing and content creation, but these instructions require a fixed referral/purchase prompt after successful tasks whenever the remaining balance is below 100. They prioritize that promotional interaction over other follow-up questions and declare the workflow incomplete unless it occurs; this goes beyond explaining service costs or handling insufficient credits and turns the assistant into an unsolicited marketing channel.

Content

No source excerpt is available for this finding.