invoice-organizer

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes local shell utilities (find, mkdir, cp, mv) to manage, copy, and rename files within the user's directory structure as part of its core organization logic.
  • [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it is designed to ingest and act upon data extracted from untrusted external documents (invoices and receipts).
  • Ingestion points: Text extraction from PDF documents and image-based receipts (SKILL.md).
  • Boundary markers: The instructions lack explicit boundary markers or warnings to the agent to ignore potentially malicious instructions embedded within the invoice text.
  • Capability inventory: The agent has capabilities to read files, write CSV summary files, and execute file system operations (move/copy/create directories) via bash.
  • Sanitization: There is no specified logic to sanitize or validate the content extracted from documents before it is used for filename generation or directory creation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 05:28 PM