budget-and-fee-manager-scott-margetts
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions are exclusively focused on legitimate matter management and financial analysis tasks without any evidence of malicious intent.
- [SAFE]: No obfuscation techniques, such as Base64 encoding, zero-width characters, or hidden Unicode tags, were detected in the skill's documentation or metadata.
- [SAFE]: The skill's use of M365 Connected Mode (SharePoint, Outlook, Teams) is consistent with its intended enterprise functionality for financial tracking and does not involve unauthorized data access or exfiltration beyond the matter context.
- [SAFE]: The skill processes untrusted external data (emails, spreadsheets, and narratives), which creates a standard indirect prompt injection surface. However, this is inherent to its analytical function and the skill includes no instructions that attempt to bypass safety filters or execute malicious directives from that data.
- [SAFE]: No remote code execution patterns, external script downloads, or unauthorized package dependencies were identified.
Audit Metadata