ClawHub
Back to skill

Security audit

爆款拆解｜抖音小红书爆款视频拆解（引用逐字核对原文）

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed LinkDigest wrapper for analyzing user-provided social-media links, with the main privacy consideration that submitted links and results go to an external service.

Install only if you are comfortable sending submitted public links or share text to LinkDigest using your API key. Avoid private, deleted, login-only, or sensitive links because results may be cached by link; prefer the bundled Python script or curl path, and review/pin mcp-remote before using the optional npx MCP setup.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

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 77)May include surrounding context.

直接调 HTTP（没有 Python 时）

bash
curl -sS -X POST https://linkdigest.dev/api/v1/digest \
  -H "Authorization: Bearer $LINKDIGEST_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://v.douyin.com/<短链>/", "format": "json", "breakdown": true}'

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The text states that Chinese breakdowns use a Chinese missing message while English breakdowns use an English message, and elsewhere the skill is primarily documented around Chinese defaults. This suggests a fixed language behavior path rather than consistently offering a user choice at output time, which can violate language/locale neutrality expectations.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding

The skill instructs users to run npx mcp-remote without pinning a package version or integrity, which can cause execution of a newer or compromised package from the npm registry. This creates a supply-chain risk because the fetched code runs locally and may access environment variables, network, or user data depending on the client context.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.