saas-legal-generator

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill serves as a local drafting utility. It takes structured information from a JSON configuration file or interactive CLI prompts and populates Markdown templates to generate preliminary legal documents. The logic is entirely local and transparent.\n- [SAFE]: The generation script (scripts/index.ts) is designed for execution within the Bun runtime on the user's machine. It uses native modules for file system interaction and terminal input, and does not include any network calls, unauthorized persistence, or command execution functionality.\n- [SAFE]: Documentation and instructions include references to well-known legal and regulatory authorities, such as the UK Information Commissioner's Office and the California Department of Justice, providing users with links to official sources for compliance research.\n- [INDIRECT_PROMPT_INJECTION]: The skill features a data ingestion surface where user-supplied content is interpolated into templates.\n
  • Ingestion points: Data is collected from a local config.json file or via interactive terminal prompts.\n
  • Boundary markers: The script performs direct string replacement using the replaceAll method without employing specific delimiters or instruction-override warnings for the agent.\n
  • Capability inventory: The script possesses capabilities for local file read and write operations via node:fs/promises.\n
  • Sanitization: The escapeCell function provides sanitization for Markdown table entries by escaping pipes and replacing newlines with HTML break tags.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 04:53 PM