invoice-organizer
Pass
Audited by Gen Agent Trust Hub on Jun 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses local shell commands such as
find,mkdir,cp, andmvto manage the filesystem and organize files into a structured directory system based on extracted metadata.- [PROMPT_INJECTION]: The skill processes untrusted content from invoices and receipts, which introduces a surface for indirect prompt injection. - Ingestion points: Content is extracted from PDF, JPG, and PNG files located in user-specified directories.
- Boundary markers: The instructions lack explicit delimiters or "ignore embedded instructions" warnings for the agent when processing extracted text.
- Capability inventory: The skill has the capability to create directories and move or copy files within the filesystem.
- Sanitization: There is no evidence of sanitization or validation logic for the extracted data before it is used for file renaming or CSV generation.
Audit Metadata