Back to skill

Security audit

快手达人数据 SocialDataX 达人信息

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because it repeatedly runs an unpinned, automatically fetched CLI that could change after review, while some scanner analysis was partial.

Consider whether you trust the CLI package and are comfortable with it being fetched at its latest version when used. The scanner did not report confirmed malicious behavior, but its review was partial: some referenced paths could not be resolved, so the available 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (10)

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 27)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

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

Medium
Category
MCP Rug Pull
Confidence
99% confidence
Finding

The auth-status instruction executes socialdatax-skills@latest through npx with automatic confirmation, rather than a reviewed, fixed version. Although this is a CLI rather than an MCP server, a compromised package release could execute with the agent's permissions and access available credentials; the documented read-only behavior does not constrain package execution.

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 27)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 interactive login alternative also executes socialdatax-skills@latest without a fixed version. Hidden input protects against casual display of the key, but a compromised release could capture the entered credential or execute other code as the local user.

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 stdin-based login instruction runs a mutable @latest package and supplies it with the user's API key. Stdin avoids command-line disclosure, but it cannot protect the key from a compromised package version receiving that input.

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 creator-search example uses npx -y with @latest, allowing executable code to change without a corresponding review of this skill. A compromised release would run with the agent's permissions and access to the configured API credential, even though the intended operation only retrieves profile 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
99% confidence
Finding

The paginated search example repeats the same mutable @latest execution dependency. Pagination is not itself dangerous, but executing an unreviewed package release creates a supply-chain path to credential theft or arbitrary actions within the runtime'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 user-ID profile lookup executes a package selected by the mutable latest tag. The profile lookup is a legitimate read-only task, but a compromised package release would not be technically restricted to that behavior and could access credentials or other permitted 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
99% confidence
Finding

The profile-URL lookup also invokes an unpinned @latest package with automatic confirmation. This is another instance of the same supply-chain weakness, not evidence that the profile URL or the service 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.