fondo-sdk-patterns
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external financial data exports (CSV and REST API responses), which creates a surface for indirect prompt injection if the data contains malicious instructions. However, the skill explicitly mandates security controls to mitigate this risk.
- Ingestion points: Processes bulk financial data imports from CSV files and transaction data from Fondo REST endpoints described in
SKILL.md. - Boundary markers: Instructions require validating source schema and using field allowlists before parsing or forwarding data.
- Capability inventory: Uses the
fetchAPI for network operations and requestsRead,Write, andEdittool permissions. - Sanitization: Mandates the use of Zod validation for structured CSV parsing and requires quarantining unknown fields for manual review.
Audit Metadata