Skip to content

Security: whispr-dev/resonant-llm

Security

SECURITY.md

Security Policy

Responsible Disclosure

If you discover:

  • A memory disclosure bug
  • A prompt-injection persistence vector
  • A behavior hijack vulnerability

Do not file a public issue.

Instead, report privately:

Method Address
Email security@whispr.dev

We respond within 72 hours.

Scope

Resonant LLM operates locally. Security focus areas:

  • Isolation of memory logs
  • Protection of local microphone/audio access
  • Prevention of injected code through pipeline text paths

Verification

Users are encouraged to:

  • Inspect and audit source code before deployment
  • Run models offline (no network access recommended)

There aren’t any published security advisories