Security audit

小红书数据分析 SocialDataX 笔记详情

Security checks for vulnerabilities and agentic risk

Overview

The skill’s note lookups and optional media downloads fit its stated purpose, with ordinary dependency and API-key precautions.

Use a dedicated SocialDataX key, prefer supported secret storage, and keep any local key configuration out of version control. Prefer a reviewed, pinned CLI version over @latest and select download destinations deliberately. Only the instruction file was bundled; the external CLI’s behavior remains unverified.

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 (3)

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

Medium

Category: MCP Rug Pull
Confidence: 98% confidence
Finding: The command uses npx -y socialdatax-skills@latest, automatically executing a mutable package release rather than a reviewed, fixed version. A compromised publisher account or malicious future release could execute code with the agent's filesystem permissions and access inherited credentials, including SOCIALDATAX_API_KEY. Although the detector calls this an MCP server reference, it is a direct CLI invocation; that distinction 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 URL-based detail command also executes socialdatax-skills@latest with automatic installation approval, allowing the code executed by the agent to change without review. If a future package release is compromised, it could steal the API key or modify accessible files despite the skill describing its intended API operations as read-only.
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 optional media-download command again executes a mutable @latest package with npx -y, exposing the agent to unreviewed future releases. Not requiring an API key does not isolate the process: a compromised release could still read inherited environment variables and access files beyond the requested output directory under the agent's permissions.
Content: No source excerpt is available for this finding.