demo-script

Pass

Audited by Gen Agent Trust Hub on Mar 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is purely instructional and does not include any functional scripts or commands that interact with the system or external networks.
  • [PROMPT_INJECTION]: The skill reads from a local context file .agents/sales-context.md. Although this is a data ingestion surface, the skill does not use any tools that would enable exploitation via indirect prompt injection.
  • Ingestion point: .agents/sales-context.md (local file read)
  • Boundary markers: Not specified in instructions
  • Capability inventory: Restricted to text generation and guided conversation
  • Sanitization: Not applicable as no structured data is processed for execution
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 26, 2026, 12:37 PM