voice
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted audio data from the microphone which is transcribed into text and processed by the agent.
- Ingestion points: Voice input processed via
VoiceAssistantandVoiceRecognitionclasses as implemented inindex.tsand described inSKILL.md. - Boundary markers: There are no specified delimiters or "ignore embedded instructions" warnings for the transcribed text before it is passed to the agent context.
- Capability inventory: The skill documentation includes examples of high-value actions such as executing trades ("buy 100 dollars of Trump YES"), checking portfolio values, and setting price alerts.
- Sanitization: The implementation does not include explicit validation, filtering, or sanitization of the transcribed text before it influences agent behavior.
Audit Metadata