document-generation

Pass

Audited by Gen Agent Trust Hub on Nov 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data from external sources (JSON, database records, CRM data) into document templates.\n
  • Ingestion points: The skill body and evals/routing.yaml specify ingesting data from JSON, databases, and CRM systems for document generation.\n
  • Boundary markers: No delimiters or explicit instructions are provided to separate data from instructions within the templates.\n
  • Capability inventory: The skill utilizes powerful tools such as Puppeteer (which executes HTML and JavaScript) and various libraries for generating Word, Excel, and PDF files.\n
  • Sanitization: There are no explicit instructions for sanitizing or escaping the data before it is interpolated into the templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 16, 2026, 05:44 PM