Skills
skills/sixtysecondsapp/use60/New Deal from Meeting/Gen Agent Trust Hub

New Deal from Meeting

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing untrusted meeting transcripts to perform CRM actions. 1. Ingestion points: Full transcript text retrieved via the get_meeting_transcript action. 2. Boundary markers: Absent; there are no instructions or delimiters used to separate user-provided data from system instructions. 3. Capability inventory: The skill utilizes create_deal and create_task capabilities to modify CRM data. 4. Sanitization: Absent; the skill does not validate or filter the extracted information for malicious content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 11:37 AM