israeli-financial-reports
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted financial data provided by users, such as Transaction Journals and Trial Balances, to generate reports. This creates an attack surface where malicious instructions could be embedded within the financial data to influence the agent's behavior during the report generation process.
- Ingestion points: User-provided transaction journals, trial balance data, and opening balances (SKILL.md Step 2 and Step 3).
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the financial data inputs.
- Capability inventory: The skill utilizes Bash (Python) for report generation and file write/edit permissions to export results in PDF, Excel, and CSV formats.
- Sanitization: There is no explicit requirement for the agent to sanitize or validate the content of the financial data beyond ensuring numerical balance (debits = credits).
Audit Metadata