ClawHub
Back to skill

Security audit

小红书竞品研究

Security checks for vulnerabilities and agentic risk

Overview

The skill coherently supports read-only competitor research through SocialDataX, with ordinary privacy and third-party software considerations.

Search topics and parameters go to SocialDataX and may consume credits, so avoid confidential queries unless you intend to share them. Prefer a reviewed, fixed CLI version and supported secret storage. This review inspected the complete bundled skill instructions; it could not verify the external CLI implementation or publisher provenance.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
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, which permits downloading and executing a changing package version without an interactive installation confirmation. A compromised future release could execute with the agent's filesystem access and available credentials, including SOCIALDATAX_API_KEY; the skill's read-only description does not constrain package execution. This is a direct CLI invocation rather than an MCP server reference, but the unpinned dependency risk remains valid.

Content

No source excerpt is available for this finding.

The search workflow sends user-provided research keywords to SocialDataX without an explicit privacy disclosure.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The skill instructs the agent to execute SocialDataX searches using keywords derived from the user's research intent (line 51), but does not warn that those keywords are transmitted to a third-party service. The read-only assurances at lines 88 and 109 address account modifications, not disclosure of potentially confidential research topics or business plans.

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 second search example repeats the mutable npx -y socialdatax-skills@latest execution pattern, exposing the same supply-chain risk as the first command. If the resolved release or its dependencies are compromised, running this research workflow could expose the agent's credentials and accessible files despite the intended read-only API operation. This is a duplicate exposure of the same root cause, not evidence of a separate compromise.

Content

No source excerpt is available for this finding.