financial-due-diligence

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to provide structured templates for verifying financial data, assessing asset quality, and identifying liabilities. It does not perform automated actions or execute scripts.
  • [DATA_EXPOSURE]: The skill references a configuration file at ../../CLAUDE.md. This is a standard pattern for loading shared environment-level preferences and does not involve unauthorized access or exfiltration of sensitive information.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external data such as financial reports provided by the user.
  • Ingestion points: User-supplied due diligence reports and financial statements.
  • Boundary markers: Absent; the skill relies on the user to provide content directly for review.
  • Capability inventory: None; the skill does not possess tools for network access, file system modification, or command execution.
  • Sanitization: Absent; the skill processes text inputs without explicit filtering, but its lack of executable capabilities mitigates this risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 02:25 AM
Security Audit — agent-trust-hub — financial-due-diligence