walkie-talkie-hardened

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests and transcribes incoming WhatsApp audio messages (Workflow step 1: "When a user sends an audio/ogg/opus file: Use tools/transcribe_voice.sh to get the text. Process the text as a normal user prompt."), so untrusted third-party (user-generated) content is read and directly influences the agent's decisions and actions, enabling indirect prompt injection.