ClawHub
Back to skill

Security audit

X Growth Operator / X 增长运营助手

Security checks across malware telemetry and agentic risk

Overview

The skill is mostly coherent for review-first X account operations, but it exposes live posting paths that are not fully protected by server-side approval or authentication.

Install only if you are comfortable giving the skill credentials that can post to your X account. Keep `scripts/.env` private, use least-privilege tokens if possible, avoid leaving the dashboard running, and review any live action before execution; the publisher should add server-side approval/authentication and document the Desearch network endpoint before this is treated as low-risk.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill declares powerful capabilities in metadata and workflow steps—environment variable access, local file read/write, network access, and shell execution—but does not expose a clear permissions model or user-facing permission declaration. In a skill that can perform authenticated X actions and persist data locally, this gap increases the risk of overbroad execution and weak user awareness about what the skill can do.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The /api/execute endpoint allows callers to trigger live external actions in x-api mode, which can post or otherwise act on X once a draft exists, but this file implements no authentication, no CSRF protection, and no explicit user-confirmation or warning at execution time. In the context of a growth-operations skill designed to monitor discussions and execute approved actions, this is more dangerous because the server exposes a direct action surface that could be abused by any local process, malicious webpage via localhost access patterns, or an unintended client workflow.

Credential Access

High
Category
Privilege Escalation
Content
- node
        - npm
      config:
        - scripts/.env
    primaryEnv: X_API_KEY
    install:
      - kind: node
Confidence
88% confidence
Finding
.env

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.