ip-rotation

Warn

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to download source code from unverified personal GitHub repositories.
  • Evidence: git clone https://github.com/isPique/Tor-IP-Changer and git clone https://github.com/gr33n37/gr33n37-ip-changer in SKILL.md.
  • [REMOTE_CODE_EXECUTION]: The installation instructions execute scripts from these downloaded untrusted repositories.
  • Evidence: pip install -r requirements.txt and python setup.py install are executed within the cloned directories in SKILL.md.
  • [COMMAND_EXECUTION]: The skill uses shell commands to install and configure external utilities.
  • Evidence: Use of git clone, cd, pip install, and python setup.py install in SKILL.md.
  • [PROMPT_INJECTION]: The skill processes data from external web services (YouTube, Search APIs) without explicitly defined sanitization or boundary markers, creating a surface for indirect prompt injection.
  • Ingestion points: Responses from external services mentioned in the 'When to Use' section of SKILL.md (e.g., YouTube, Brave Search).
  • Boundary markers: Not specified in the skill instructions.
  • Capability inventory: Shell command execution and file system modification through the installation of third-party tools.
  • Sanitization: No evidence of validation or sanitization for external content is provided.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 19, 2026, 05:47 AM
Security Audit — agent-trust-hub — ip-rotation