invoice-organizer

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFENO_CODECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [NO_CODE]: The skill does not bundle any scripts, binaries, or configuration files; it relies entirely on natural language instructions and standard shell utilities.
  • [COMMAND_EXECUTION]: The skill directs the agent to execute shell commands such as find, mkdir, cp, and mv to identify, sort, and rename files on the local filesystem.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it extracts and processes text from untrusted external documents (PDFs and images).
  • Ingestion points: Content extraction from invoices and receipts as described in the instructions.
  • Boundary markers: No specific delimiters are used to separate extracted content from agent instructions.
  • Capability inventory: File system access via shell commands (find, mkdir, cp, mv) and file creation (csv report).
  • Sanitization: No explicit sanitization or validation of extracted text is mentioned before it is used to generate filenames or directory structures.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 05:30 PM