persona-reference-architecture

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches identity verification data from the Persona API (withpersona.com), which is a well-known identity and KYC service provider.
  • [INDIRECT_PROMPT_INJECTION]: The provided Python script ingests data from external API responses and prints it to the console.
  • Ingestion points: Data is received via the requests.get call in SKILL.md.
  • Boundary markers: None present.
  • Capability inventory: The script is limited to network read operations and printing specific JSON attributes (id, status).
  • Sanitization: No specific sanitization is applied, but the risk is minimized by only accessing and displaying specific structured data fields rather than executing or interpolating raw content into agent instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 03:36 PM
Security Audit — agent-trust-hub — persona-reference-architecture