invoice-organizer
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill extracts information from external, untrusted sources (invoices, receipts, and images), which creates a surface for indirect prompt injection.
- Ingestion points: The skill reads content from PDFs, images (JPG, PNG), email attachments, and screenshots provided in user-specified directories.
- Boundary markers: The instructions lack explicit boundary markers or directives to the agent to disregard potential instructions embedded within the processed documents.
- Capability inventory: The agent has access to file system tools including
find,mkdir,cp, andmvto restructure directories and rename files, and it can generate CSV reports. - Sanitization: There is no evidence of sanitization or validation for the text extracted from the files before it is used to construct new filenames or spreadsheet entries.
Audit Metadata