expense-report
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's primary function is to organize business expenses, which is clearly documented and supported by the provided templates. No obfuscation, data exfiltration, or remote code execution patterns were detected.
- [PROMPT_INJECTION]: The skill exposes an indirect prompt injection surface by processing untrusted user input and spreadsheet data. 1. Ingestion points: User-provided expense descriptions and external XLSX files via the read_xlsx tool. 2. Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands. 3. Capability inventory: The skill can create and analyze spreadsheets via create_xlsx and analyze_spreadsheet tools. 4. Sanitization: No explicit input validation or data sanitization is described. This surface is considered a standard operational risk for data-processing agents and does not constitute a malicious finding.
Audit Metadata