ClawHub
Back to skill

Security audit

X Analytics CLI

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed, read-only X/Twitter analytics helper that uses OAuth credentials to fetch data, with no artifact-backed evidence of posting, deletion, persistence, or hidden behavior.

Install only if you are comfortable configuring X API OAuth credentials for read-only analytics. Use a low-risk account or least-privilege tokens where possible, keep credentials out of chat and logs, and remember that searches, usernames, tweet IDs, and authenticated timeline/profile requests go to X through the CLI.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger list includes very broad terms such as "X API," "Twitter API," "X data," and "Twitter data," which can cause the skill to activate for generic requests that may not specifically require this tool. Over-broad invocation increases the chance of unnecessary authenticated API use and accidental routing of user requests into a third-party data workflow without clear intent.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs the agent to use OAuth credentials from flags, environment variables, or a local credentials file and to make authenticated requests to X, but it does not include an explicit warning about secret handling, data transmission to a third party, or avoiding credential disclosure in output/logs. In an agent setting, this omission can lead to unsafe handling of highly sensitive tokens and user data being sent externally without sufficiently clear user awareness.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.