persona-security-basics

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill implements a workflow that ingests data from the Persona API, creating an attack surface for indirect prompt injection.
  • Ingestion points: The Python script retrieves inquiry data from the Persona inquiries API endpoint.
  • Boundary markers: The instructions do not provide explicit delimiters or ignore directives to separate retrieved data from the agent's internal instructions.
  • Capability inventory: The skill has access to Read, Write, and Grep tools, and the provided code performs network GET requests.
  • Sanitization: Inquiry attributes are printed directly from the API response without validation or sanitization steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 03:37 PM
Security Audit — agent-trust-hub — persona-security-basics