ClawHub
Back to skill

Security audit

AI Topic Scout

Security checks across malware telemetry and agentic risk

Overview

The skill appears purpose-built for Twitter/X automation, but it asks users to handle live session cookies in an unsafe and under-scoped way.

Install only if you understand that `auth_token` and `ct0` are live Twitter/X session credentials. Prefer an official OAuth/API integration or a dedicated low-risk account, avoid passing cookies in command arguments, store secrets only in a protected secret manager or environment injection flow, rotate/revoke the session after use, and do not use this for accounts you cannot afford to lose.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Context-Inappropriate Capability

Medium
Confidence
97% confidence
Finding
The skill explicitly instructs operators to extract raw Twitter/X session cookies (`auth_token`, `ct0`) from the browser and pass them on the command line. Session cookies are high-value secrets that can enable account access and are exposed to shell history, process listings, logs, and accidental disclosure, making credential compromise more likely.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The instructions tell users how to obtain and use authentication cookies for scraping without meaningful safety guidance, despite those values functioning as sensitive session credentials. In this workflow, the context increases risk because the cookies are intended for repeated operational use in automation, which encourages insecure storage and reuse of live session tokens.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.