nda-generator

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided business details to generate document templates, creating a potential vector for indirect instructions.
  • Ingestion points: User-supplied context regarding business meetings, party roles, and confidential information defined in the 'How to Use Me' section.
  • Boundary markers: Absent; the instructions lack explicit delimiters or warnings to ignore instructions embedded in the user's business description.
  • Capability inventory: The skill uses the office-mcp server tools create_docx, fill_docx_template, and docx_to_pdf to generate files on the local filesystem.
  • Sanitization: No specific validation or sanitization routines are defined to filter user input before it is used in document generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 08:21 AM