meddic-call-prep-auto

Pass

Audited by Gen Agent Trust Hub on Mar 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the processing of untrusted data from multiple external ingestion points.
  • Ingestion points: Untrusted content is retrieved from HubSpot deal notes (hubspot_get_deal), Google Calendar event descriptions (gcal_get_event), and CRM activity logs via the ask_agent tool.
  • Boundary markers: The skill workflow lacks explicit delimiters or instructions to ignore embedded commands within the interpolated external data.
  • Capability inventory: The skill possesses significant capabilities, including the ability to search across CRM records (companies, contacts, deals), access user calendars, and query a CRM data warehouse.
  • Sanitization: No sanitization, validation, or filtering of the content fetched from external sources is performed before it is synthesized into the final MEDDIC brief.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 22, 2026, 06:50 PM