meddpicc-post-call
Pass
Audited by Gen Agent Trust Hub on Apr 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8).
- Ingestion points: Untrusted data enters the agent context via meeting transcripts (get_meeting_transcript), Gmail threads (gmail_read_thread), and CRM note bodies (get-note-body).
- Boundary markers: The instructions do not require the use of delimiters or boundary markers when processing these external data sources, increasing the risk that embedded instructions could be followed.
- Capability inventory: The skill possesses write capabilities including updating records (update-record), creating notes (create-note), and creating tasks (create-task) in the Attio CRM.
- Sanitization: There is no instruction to sanitize or validate the content extracted from transcripts or emails before it is used to populate CRM fields or tasks.
Audit Metadata