persona-interview

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the creation of a persona definition file by ingesting user-provided responses to interview questions.
  • Ingestion points: User responses to the 5-7 Socratic interview questions defined in the Procedure section of SKILL.md.
  • Boundary markers: Absent; the instructions do not require the use of delimiters or 'ignore' instructions when incorporating user responses into the generated SOUL.md draft.
  • Capability inventory: The skill directs the agent to generate instruction-heavy text content (SOUL.md) and provides guidance for saving it to a local configuration path (~/.hermes/profiles//SOUL.md).
  • Sanitization: Absent; there is no explicit instruction to sanitize or validate user input before it is interpolated into the generated prompt draft.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 07:41 PM
Security Audit — agent-trust-hub — persona-interview