ClawHub
Back to skill

Security audit

scavio-x

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Scavio API guide for reading X data, with disclosed endpoints and no hidden code or persistence.

Before installing, make sure you are comfortable sending X queries and handles to Scavio using your SCAVIO_API_KEY. Use the follower, following, profile, and tweet endpoints only for legitimate purposes, respect X/platform terms and applicable privacy rules, and avoid unnecessary bulk pagination or retention of personal/social graph data.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (1)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly enables collection of user profiles, followers, followings, tweets, replies, and trending data from X, but it does not warn users about privacy, data-use, retention, or compliance considerations. This increases the risk that an agent operator will gather or process personal/social graph data without appropriate consent, notice, or policy controls.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:39