Back to skill

Security audit

YouTube 视频总结|YouTube字幕提取(带时间戳,可译中文)

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed LinkDigest client for summarizing user-provided video links, with no evidence of hidden local access, persistence, or destructive behavior.

Install only if you are comfortable sending video or social-media links to linkdigest.dev with your LinkDigest API key. Use --max-credits when cost matters, and do not submit private or sensitive links unless you accept the service's remote processing and link-based result caching.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill requires environment access, shell execution, and outbound network access but does not declare any explicit tool scope such as permissions or allowed-tools. That makes the effective privilege boundary unclear and can allow broader execution or data egress than reviewers or users expect, especially because the skill handles an API key and invokes curl/python against a remote service.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest describes a YouTube-specific summary/transcript skill, but the inline CLI description says the tool reads links from multiple unrelated platforms such as 小红书、抖音、TikTok、X and 公众号文章. This is not just incomplete documentation; it affirmatively describes a broader intent than the declared skill purpose.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.