batch-inference-pipeline
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes machine learning deployment patterns, configurations, and code. This creates a surface for indirect prompt injection if the external data or documentation the agent reads contains malicious instructions intended to subvert the agent's behavior.
Audit Metadata