tax-filing

Warn

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The workflow requires the agent to dynamically generate a Python script (output/fill_YEAR.py) incorporating logic from scripts/fill_forms.py and execute it at runtime to process the tax forms.
  • [EXTERNAL_DOWNLOADS]: Fetches blank tax forms from official government repositories at irs.gov and ftb.ca.gov. These are well-known, trusted domains for the intended use case.
  • [PROMPT_INJECTION]: The skill ingests untrusted third-party data from source documents (PDFs, CSVs) provided by the user. This creates a surface for indirect prompt injection if those documents contain malicious instructions intended to divert the agent's calculation logic or data handling.
  • Ingestion points: Document extraction using pdfplumber and the agent's Read tool for CSV files.
  • Boundary markers: No explicit delimiters or boundary markers are defined for the extracted data saved to work/tax_data.txt.
  • Capability inventory: Local file read/write, network downloads from trusted sources, and Python script execution via subprocesses.
  • Sanitization: No validation or sanitization is performed on the extracted document content before it is used in tax computations or form filling.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 8, 2026, 03:23 AM