israeli-expense-categorizer
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's instructions and logic are consistent with its stated purpose of accounting and tax categorization. It does not contain any hidden commands, malicious scripts, or exfiltration patterns.
- [PROMPT_INJECTION]: The skill's workflow involves processing untrusted external data (CSV files, bank exports), which constitutes a surface for indirect prompt injection.
- Ingestion points: Expense data provided via file paths (CSV, Excel) or free-text inputs (SKILL.md, Step 1).
- Boundary markers: Absent; there are no instructions to the agent to treat the content of these files as data only or to ignore embedded instructions.
- Capability inventory: The skill allows the use of file reading, writing, and Python-based shell execution for data parsing and report generation.
- Sanitization: No validation or sanitization of input data is described in the instructions.
Audit Metadata