invoice-organizer
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from invoices and receipts (PDFs, images) to extract metadata like vendor names, dates, and amounts.
- Ingestion points: Files identified by the
findcommand and processed via text extraction tools (pdftotext, pdfplumber, tesseract-ocr) as described inSKILL.md. - Boundary markers: The instructions lack specific delimiters or explicit warnings for the agent to ignore potentially malicious text embedded within the processed documents.
- Capability inventory: The skill uses file system operations such as
mkdir,cp, andmvto organize files, and generates CSV reports based on extracted information. - Sanitization: There is no mention of sanitizing or validating extracted text before it is interpolated into file paths or CSV records, which could lead to path manipulation or schema confusion if malicious content is present in an invoice.
Audit Metadata