vietnamese-finance-copy

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to provide linguistic and regulatory guidance for Vietnamese financial content. Analysis across all threat categories indicates the implementation is safe for use.\n- [DYNAMIC_EXECUTION]: The script scripts/validate_copy.py dynamically loads additional rule sets from local files matching the rules_*.py pattern using the importlib module. This is a standard architectural choice for modularizing linter logic and is restricted to the skill's own directory.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-supplied documents for linting purposes.\n
  • Ingestion points: Local files provided as arguments to scripts/validate_copy.py and scripts/check_font_coverage.py.\n
  • Boundary markers: Not applicable as the tools analyze the full content of provided text files.\n
  • Capability inventory: Scripts perform local file reading, regex matching, and Unicode normalization (NFC).\n
  • Sanitization: Processing is limited to text analysis and standard library normalization functions; the content of the files is not executed or evaluated as code.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 07:24 AM
Security Audit — agent-trust-hub — vietnamese-finance-copy