month-end-prep
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill retrieves financial records from accounting platforms (e.g., 1C, Moysklad) and payment services (e.g., Yookassa, Tinkoff) via tool connectors to perform data reconciliation.
- [DATA_EXPOSURE]: It scans the local filesystem (defaulting to
~/Documents/Первичка) to verify the presence of supporting documents (invoices, receipts) for transactions. - [COMMAND_EXECUTION]: Generates report files in Excel and PDF formats on the user's desktop using Python libraries such as
xlsxwriterandreportlab. - [PROMPT_INJECTION]: Ingesting external data from accounting systems and CSV files creates an indirect prompt injection surface, as the agent processes content that could theoretically contain hidden instructions. However, no malicious patterns or payloads were detected in the skill's logic.
Audit Metadata