tax-filing

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides a structured framework for tax-related tasks. It utilizes text-based templates and placeholders for financial data, which are benign.
  • [DATA_EXFILTRATION]: While the skill mentions reading a configuration file (../../CLAUDE.md) and accessing ERP data, it does not contain any logic to transmit this data to external or unauthorized destinations.
  • [PROMPT_INJECTION]: The skill processes external data from ERP systems. While it lacks explicit boundary markers or sanitization instructions for this data, it also lacks dangerous capabilities (like file writing or network requests) that could be exploited via injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 02:25 AM
Security Audit — agent-trust-hub — tax-filing