gl-recon
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFE
Full Analysis
- Proactive Security Instructions: The skill includes a specific directive to treat subledger and custodian extracts as untrusted data. This is an effective defense against indirect prompt injection, where instructions might be embedded within processed data.
- Data Normalization: The skill defines a normalization process that includes type coercion and formatting of identifiers. This acts as a functional validation layer, helping to ensure data integrity during processing.
Audit Metadata