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