financial-document-parser

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill's primary function is to ingest and process untrusted external data (financial documents), which introduces a vulnerability surface for indirect prompt injection.
  • Ingestion points: User-provided PDFs or images of invoices, receipts, and bank statements mentioned in the "When to Use This Skill" section.
  • Boundary markers: Absent. The instructions do not define specific delimiters or provide guidance to the agent to disregard instructions that might be embedded within the documents being parsed.
  • Capability inventory: No executable capabilities (scripts, shell commands, or network access) are defined within this skill file.
  • Sanitization: Absent. There are no instructions for the agent to sanitize extracted content or validate it before generating output.
  • [No Code] (SAFE): This skill contains no executable scripts, binaries, or configuration files. It consists entirely of YAML metadata and Markdown instructions for the LLM.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:33 PM