rtl-css

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • PROMPT_INJECTION (SAFE): No malicious instructions or bypass attempts were found in the markdown content or metadata.
  • DATA_EXFILTRATION (SAFE): The skill does not perform any network operations or access sensitive system files. It only scans local source code for CSS class patterns.
  • COMMAND_EXECUTION (SAFE): The scripts/audit_rtl.sh file uses the standard grep utility to search for specific strings (pl-, pr-, etc.) within local .tsx and .jsx files. This is a read-only operation and is safe for its intended purpose.
  • EXTERNAL_DOWNLOADS (SAFE): No remote scripts are downloaded or executed. The skill references the rtl-detect library in a code snippet, which is a standard utility for language direction detection.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:32 PM