Security audit

抖音视频解析下载（KK定制版）

Security checks for vulnerabilities and agentic risk

Overview

The skill’s Douyin download/transcription purpose is coherent, but it relies on unverified local analyzer code and an external parsing service, so it belongs in Review before installation.

Install only if you trust and have verified the separate douyin-analyzer MCP code, because this skill does not bundle or pin it. Treat supplied Douyin links as potentially shared with Douyin and liuxingw.com, and delete any downloaded videos or transcripts from /tmp when finished.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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

Findings (2)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:44
Finding: Unverified External Python Dependency Can Execute Arbitrary Local Code
Content: View full analysis
Remediation: View remediation

other

Note

Location: SKILL.md:65
Finding: Undisclosed Sharing of User-Supplied Links With a Third-Party Parsing Service
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The skill explicitly instructs users or agents to download a remote video to a local path under /tmp but does not clearly warn that it will create local files, how long they will remain, or whether sensitive media may persist after use. In an agent setting, silent local writes can expose disk contents to later processes, leak private media, or accumulate untracked artifacts, especially when combined with transcription and content analysis workflows.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.