meeting-notes

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted meeting transcripts without security boundaries.
  • Ingestion points: Raw meeting notes and transcripts provided as user input (SKILL.md).
  • Boundary markers: None defined; the skill lacks delimiters or instructions to ignore commands within the data.
  • Capability inventory: The skill uses the 'create_docx' MCP tool to generate files.
  • Sanitization: No validation or sanitization of input data is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 05:18 AM