persona-core-workflow-b

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill interacts with the official Persona API (withpersona.com) to perform identity verification tasks. This is a well-known identity verification service and the interaction is limited to standard API requests.
  • [SAFE]: Sensitive API keys are accessed through environment variables (os.environ['PERSONA_API_KEY']), which is a recommended security practice for secret management and prevents credential exposure.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests identity and verification data from the Persona API, creating a potential surface for indirect prompt injection. However, as this data processing is central to the skill's primary purpose and originates from a well-known service, the risk is considered minimal and inherent to the functionality.
  • Ingestion points: Data extracted from Persona API responses in SKILL.md (e.g., name-first, name-last, birthdate, and check status reasons).
  • Boundary markers: The instructions do not define specific delimiters or isolation instructions for API-returned data.
  • Capability inventory: The skill has access to the Write, Edit, and Bash tools as defined in the frontmatter configuration.
  • Sanitization: Data is parsed directly from JSON responses without additional validation or filtering layers.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 03:37 PM
Security Audit — agent-trust-hub — persona-core-workflow-b