insurance-advisor

Pass

Audited by Gen Agent Trust Hub on Sep 29, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill is comprised entirely of Markdown files containing instructions, templates, and examples. It does not include any scripts, executables, or external software dependencies.
  • [SAFE]: The instructions implement a structured advisory role using recognized frameworks like DIME (Debt, Income, Mortgage, Education) for life insurance and standard classification for health and automotive insurance. It includes mandatory constraints requiring the AI to display legal disclaimers and advising users to consult licensed professionals.
  • [INDIRECT_PROMPT_INJECTION]: The skill acts as a data processor for sensitive user information (financial status, health conditions, family profile). While this creates an ingestion surface for untrusted data, the skill lacks dangerous capabilities—such as network exfiltration, file system modification, or command execution—that could be exploited by malicious payloads embedded in the user's data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 29, 2026, 04:02 PM