furusato
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from receipt images via OCR sub-agents, representing an ingestion point for external untrusted data. This data is used to populate local records. The skill implements a dual-verification workflow requiring the user to confirm or correct the extracted values before registration, which acts as a manual mitigation for potential data-driven influence.\n- [COMMAND_EXECUTION]: The skill makes frequent use of local CLI tools and Python scripts (e.g.,
shinkoku,import_data.py,furusato.py) to manage donation records, read files, and calculate tax limits. These commands are executed within the local environment and are scoped to project-specific database and configuration paths.
Audit Metadata