voice-generation
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes natural language text from user messages or external sources to generate voice audio, which introduces a vulnerability to indirect prompt injection if that text is sourced from untrusted external data.
- Ingestion points: Text content within the
messagesarray in the API request examples inSKILL.md. - Boundary markers: Absent. The skill does not define specific delimiters or instructions for the agent to ignore potentially malicious commands embedded within the text intended for speech synthesis.
- Capability inventory: Uses
Bash(curl *)to send content to external API endpoints. - Sanitization: Absent. The instructions do not specify any validation, escaping, or filtering of the input text before transmission to the voice generation service.
Audit Metadata