Back to skill

Security audit

抖音达人数据 SocialDataX 达人作品

Security checks for vulnerabilities and agentic risk

Overview

The skill is rated suspicious because it repeatedly runs an unpinned, automatically approved CLI package that could change between releases, though the scan did not establish malicious intent.

Before installing, consider whether you are comfortable running a CLI package that is not pinned to a reviewed version, including when entering an API key. Confirm what profile information is sent to SocialDataX, and use a reviewed fixed package version if available. The scan was partial because some local references could not be resolved, so the evidence is incomplete.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (9)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 25)May include surrounding context.

md
configuration; handle command, permission and malformed-file errors as reported instead of treating every failure as a missing Key. Authenticated hosted MCP keeps its current connection authentication and needs no separate local CLI setup.
- If missing, have the user obtain a Key from the official URL above and run `npx -y socialdatax-skills@latest auth login` in their own local terminal, entering it at the hidden prompt. The CLI saves it under that terminal user's home at `.config/socialdatax/credentials.json`, with mode 600 on Unix or a private current-user ACL on Windows; saving fails if permissions cannot be restricted. Never put the Key in AI chat, model-captured input, logs, screenshots, command history, Skill files or version control. The Agent must not read or display credential-file content.
- Each CLI invocation reads the private user file without depending on a client loading shell configuration or changing client/system settings. A nonempty `SOCIALDATAX_API_KEY` has priori

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

Medium
Category
MCP Rug Pull
Confidence
98% confidence
Finding

The authentication check executes socialdatax-skills@latest through npx with automatic approval, rather than a reviewed, immutable version. A compromised future release could execute with the agent's permissions and access environment credentials or local files even before any business request occurs; the documented credential protections do not constrain malicious package code.

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 login instruction runs the mutable socialdatax-skills@latest release and asks the user to enter an API key into that process. If the release is compromised, a hidden prompt and restrictive credential-file permissions cannot prevent the executing package from stealing the supplied key.

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 user-posts example automatically executes the mutable @latest npm release. A compromised release could access the API key and other resources available to the process, so the skill's read-only business purpose does not make the local execution 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 profile-URL user-posts command executes socialdatax-skills@latest with npx automatic approval. This introduces the same mutable-dependency execution risk as the other examples, including potential credential theft or unauthorized local actions if an upstream release is compromised.

Content

No source excerpt is available for this finding.

No explicit disclosure that user-supplied profile URLs or share text are transmitted to SocialDataX.

Medium
Category
Output Handling
Confidence
86% confidence
Finding

The workflow directs the agent to submit a user-provided profile URL or complete share text through the SocialDataX CLI, but does not warn that this input is sent to a third-party service. The read-only safety statement addresses account modifications and local credentials, not disclosure of submitted data.

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 user-series command runs an unpinned @latest npm release with the caller's privileges. Although the requested API operation is read-only, compromised dependency code could steal credentials or modify accessible local resources.

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 profile-URL user-series example automatically executes a mutable npm release rather than a pinned, reviewed artifact. A malicious upstream update could run with access to the CLI's credentials and local user permissions; this is a shared supply-chain weakness, not evidence that the current package is malicious.

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.