add-voice
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements a duplex audio path for real-time speech interaction. This capability introduces a vulnerability to indirect prompt injection, as malicious instructions could be embedded in the audio processed from the user's environment and interpreted by the underlying model.
Audit Metadata