text-to-speech
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill refers to external setup instructions hosted on GitHub and suggests adding additional CLI skills via npx, referencing the inference.sh ecosystem infrastructure.\n- [INDIRECT_PROMPT_INJECTION]: The core functionality of processing text for speech synthesis creates a surface where malicious instructions could be embedded in the input data.\n
- Ingestion points: The skill takes text input via the
--inputargument passed to thebeltCLI through theBashtool as shown in SKILL.md examples.\n - Boundary markers: Usage examples do not demonstrate the use of delimiters or specific warnings to ignore instructions embedded within the user-supplied text.\n
- Capability inventory: The skill possesses the capability to execute shell commands using the
Bashtool, specifically scoped to thebeltCLI.\n - Sanitization: The documentation does not specify or implement any validation or sanitization of the input text before it is passed to the execution environment.
Audit Metadata