ClawHub
Back to skill

Security audit

抖音文案提取

Security checks for vulnerabilities and agentic risk

Overview

The skill provides a clearly scoped video-transcription workflow, with ordinary precautions needed for downloaded software and API-key storage.

Expect selected video references to be processed by SocialDataX using your API key and potentially paid credits. Keep the key in supported secret storage and out of chat and version control. Consider using a reviewed, fixed CLI version with limited local permissions. This review covers the supplied instructions, not the downloaded CLI or hosted service.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (4)

MCP server referenced without pinned version: 'npx -y socialdatax-skills'.

Medium
Category
MCP Rug Pull
Confidence
98% confidence
Finding

The actual command executes socialdatax-skills@latest through npx -y, automatically accepting installation of a mutable package version rather than a reviewed, fixed release. A compromised publisher account or malicious future release could execute code with the agent's permissions and access the API key supplied in its environment; the fact that this is a direct CLI rather than an MCP server does not remove the supply-chain risk.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx -y socialdatax-skills'.

Medium
Category
MCP Rug Pull
Confidence
98% confidence
Finding

The aweme-id invocation also uses npx -y socialdatax-skills@latest, allowing the executable package to change without a corresponding skill review. If a future release is compromised, it can run with the agent's privileges and read the runtime API key; selecting a video by ID does not constrain the package's local capabilities.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx -y socialdatax-skills'.

Medium
Category
MCP Rug Pull
Confidence
98% confidence
Finding

The job-status command executes the same mutable @latest package even though its intended operation is only checking an existing job. A compromised release could execute arbitrary code and access environment credentials before performing any status request; the skill's credential-handling precautions do not protect against code running inside that process.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx availability'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.