fondo-cost-tuning
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected in the skill instructions. The content consists of business process guidelines, ROI calculations, and service plan comparisons.
- [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface by instructing the agent to process financial data. However, it incorporates robust safety guardrails:
- Ingestion points: The skill processes "current data" and "contract/billing information" (SKILL.md).
- Boundary markers: Explicit instructions require the agent to verify that no individual account, payroll, or tax information is copied into the analysis.
- Capability inventory: The skill uses standard file manipulation tools (Read, Write, Edit) but provides no scripts for automated data exfiltration.
- Sanitization: The instructions mandate keeping evidence redacted and reversible, and routing complex decisions to human professionals.
Audit Metadata