fondo-performance-tuning

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill consists of procedural instructions and best practices for optimizing accounting workflows in the Fondo SaaS platform. It provides helpful examples for categorization and communication strategies.
  • [INDIRECT_PROMPT_INJECTION]: The skill includes instructions for processing external data exports (CSV files). The risk is mitigated by explicit instructions to use synthetic/sample data for testing and to redact all financial data in diagnostics before processing.
  • Ingestion points: CSV reports exported from the Fondo Dashboard.
  • Boundary markers: Explicit instructions to "Redact all financial data in performance diagnostics" and "Do not include account numbers, transactions, tax documents, or credentials."
  • Capability inventory: The skill uses Read, Write, Edit, and Grep tools for file management and script modification.
  • Sanitization: Relies on user-led redaction and the use of fictional/synthetic datasets as specified in the "Prerequisites" and "Examples" sections.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:44 AM
Security Audit — agent-trust-hub — fondo-performance-tuning