meddpicc-gap-audit

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted external data (meeting transcripts and email threads) to perform deal audits and reconcile CRM fields.
  • Ingestion points: Meeting transcripts and email threads provided as primary input in SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters or "ignore" instructions to prevent the agent from potentially obeying commands embedded within the transcript or email content.
  • Capability inventory: The skill is designed to write reconciled values back to a connected CRM system, representing a high-value target for manipulation.
  • Sanitization: There is no documentation of input sanitization or filtering for the processed external content to mitigate instruction leakage.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 07:07 AM
Security Audit — agent-trust-hub — meddpicc-gap-audit