kb-article

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFE
Full Analysis
  • Indirect Prompt Injection Surface: The skill is designed to ingest and summarize ticket data and customer interactions. Because this content originates from external sources, there is a theoretical surface for indirect prompt injection if the source material contains instructions intended to override agent behavior. This is a common characteristic of skills that process external support data, and can be mitigated by ensuring the agent treats source material as data rather than instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 11:26 PM
Security Audit — agent-trust-hub — kb-article