Back to skill

Security audit

小红书数据分析 SocialDataX 笔记搜索

Security checks for vulnerabilities and agentic risk

Overview

The skill is rated suspicious because scanners flagged broad activation wording and repeated use of a CLI fetched as the unpinned latest version; scan coverage is partial.

Consider the suspicious rating and avoid installing until you are comfortable with the unpinned CLI and broad activation wording. The scan was partial: although it reports one Markdown file scanned and no executable scripts, reference resolution was incomplete, so the evidence does not establish that all related material was reviewed.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 22)May include surrounding context.

md
ion and authorized configuration, send it as stdin to `npx -y socialdatax-skills@latest auth login --stdin` for persistent CLI storage; do not request duplicate manual entry, pass it as a CLI argument, or write it to a temporary script file. Otherwise direct the user to the official URL above and hidden input with `npx -y socialdatax-skills@latest auth login` in their local terminal, without asking them to send it in chat. The CLI saves it under the execution user's home at `.config/socialdatax/credentials.json`, Unix mode 600 or a private current-user ACL on Windows. Do not repeat the Key in replies, output logs, screenshots, command examples, 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 priority, then the existing legacy variable, then the file. Saving a file

The activation instruction includes generic research tasks without requiring a Xiaohongshu/XHS context.

Medium
Category
Trigger Abuse
Confidence
90% confidence
Finding

The activation sentence lists generic tasks such as competitor research and market observation as independent reasons to use an XHS-specific service. Although the title and metadata provide platform context, this wording can steer unrelated research into third-party API calls, potentially disclosing research terms or consuming paid credits without a clear platform-specific request.

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
99% confidence
Finding

The authentication check executes socialdatax-skills@latest through npx with automatic confirmation, rather than an immutable, reviewed version. Although this is a CLI rather than an MCP server, a compromised package release could execute with the agent's permissions and access credentials even during the supposedly non-paid status check.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 22)May include surrounding context.

md
an explicit Key change. When the user has already supplied a Key in the installation prompt or current conversation and authorized configuration, send it as stdin to `npx -y socialdatax-skills@latest auth login --stdin` for persistent CLI storage; do not request duplicate manual entry, pass it as a CLI argument, or write it to a temporary script file. Otherwise direct the user to the official URL above and hidden input with `npx -y socialdatax-skills@latest auth login` in their local terminal, without asking them to send it in chat. The CLI saves it under the execution user's home at `.config/socialdatax/credentials.json`, Unix mode 600 or a private current-user ACL on Windows. Do not repeat the Key in replies, output logs, screenshots, command examples, 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

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

Medium
Category
MCP Rug Pull
Confidence
99% confidence
Finding

The auth login --stdin command dynamically executes socialdatax-skills@latest while receiving an API key. If the resolved release is compromised, it could capture that key or execute other actions; using stdin prevents some accidental disclosure but does not protect against a malicious executable.

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
99% confidence
Finding

The interactive auth login example also uses a mutable @latest release with npx automatic confirmation. Hidden terminal input reduces exposure in chat or logs, but a compromised CLI release would still receive the entered credential and run with the user's permissions.

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
99% confidence
Finding

The search example executes socialdatax-skills@latest rather than a fixed release. A compromised future release could access the execution environment and available credentials, so the documented read-only search operation does not constrain what the downloaded code can actually do.

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
99% confidence
Finding

The multi-page search example repeats the mutable @latest execution pattern. This is another instance of the same supply-chain weakness, not a separate MCP configuration issue; exploitation would require control of the resolved package or its executable dependency chain.

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.