ClawHub
Back to skill

Security audit

敏感词检测与违禁词检查

Security checks for vulnerabilities and agentic risk

Overview

The skill performs its disclosed text-checking task, with routine cautions about stored submissions and an automatically updated software dependency.

Submit only text you are comfortable having SocialDataX store, and consider service charges. Prefer a reviewed, fixed CLI version and limit its local permissions. The external npm payload is not bundled with this skill, so its implementation and future releases are outside this artifact review.

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 (1)

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

Medium
Category
MCP Rug Pull
Confidence
98% confidence
Finding

The documented command uses npx -y socialdatax-skills@latest, which automatically executes a mutable npm release rather than a reviewed, fixed version. A compromised publisher account or malicious future release could execute code with the agent's local permissions and access the SOCIALDATAX_API_KEY, submitted text, and other accessible resources. Although this is a direct CLI command rather than an MCP server launch, the unpinned-execution risk still applies, and the skill's read-only claims do not constrain package code.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.