building-with-llms

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Prompt Injection (SAFE): The skill has a surface for indirect prompt injection as it ingests user context, though it provides tools to mitigate this. 1. Ingestion points: User-provided product context. 2. Boundary markers: Absent. 3. Capability inventory: Text and file generation. 4. Sanitization: Built-in red-teaming templates.
  • SAFE (SAFE): No executable code, remote downloads, or credential leaks were detected. The skill promotes safety and least-privilege operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 03:52 PM