sgc-mobile-adapt

Pass

Audited by Gen Agent Trust Hub on Nov 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a well-structured development tool designed to improve mobile responsiveness in web applications. It follows a clear workflow of scanning, user confirmation, and applying best-practice fixes.
  • [DATA_EXPOSURE]: The local scanner script (scripts/scan_mobile_issues.py) implements security best practices by skipping sensitive directories such as .git, .next, and node_modules. It limits its analysis to relevant web file extensions (.html, .css, .jsx, etc.) and enforces a 512KB file size limit to prevent resource exhaustion or scanning of large binary files.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a defined surface for indirect prompt injection as it processes untrusted local project files.
  • Ingestion points: scripts/scan_mobile_issues.py reads content from files within the user-specified project path.
  • Boundary markers: Not present during the file reading phase.
  • Capability inventory: The skill has no file-writing, network communication, or shell-execution capabilities associated with the processing of scanned data, effectively neutralizing the risk of malicious instructions in the code being executed or exfiltrated.
  • Sanitization: The script uses strict regular expressions to extract specific CSS and HTML attributes, which prevents arbitrary content from influencing the scanner's output beyond identified layout issues.
  • [REMOTE_CODE_EXECUTION]: No remote code execution patterns were detected. The skill dependencies are explicitly stated to be zero, and the logic is entirely self-contained within the provided Python script and reference files.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 18, 2026, 10:05 AM