neo-user-journey

Warn

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill is a 'stub' that provides instructions to download and install its complete logic from a third-party GitHub repository: github.com/Cornjebus/neo-user-journey. This repository is not associated with a known trusted organization.
  • [COMMAND_EXECUTION]: The skill provides and encourages the execution of shell commands, specifically grep for system checks and npx skills add for installing remote code. It explicitly suggests using the ! prefix (Dynamic Context Injection syntax) to execute these commands directly within the agent environment.
  • [PROMPT_INJECTION]: The skill processes untrusted data from live URLs using Playwright for UX testing. This creates a surface for indirect prompt injection where malicious instructions embedded in a target website could attempt to influence the agent's behavior.
  • Ingestion points: Website content from live or localhost URLs provided by the user (SKILL.md).
  • Boundary markers: None present to distinguish between instructional text and data being audited.
  • Capability inventory: Shell command execution (npx, grep), network access for web testing, and installation of external skills.
  • Sanitization: No evidence of sanitization or filtering of external content before analysis.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 25, 2026, 06:33 PM
Security Audit — agent-trust-hub — neo-user-journey