use-voice-typing-for-fast-prompts
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is entirely instructional and consists of markdown documentation. It does not include any executable scripts, shell commands, or automated configuration changes.- [INDIRECT_PROMPT_INJECTION]: The skill provides a template that incorporates user-provided dictation into a prompt, which is a standard surface for indirect injection. However, since the skill's scope is limited to text drafting without access to sensitive systems, the risk is negligible.
- Ingestion points: The 'Master Voice Cleanup Prompt Modifier' section in SKILL.md uses a placeholder for '[SPOKEN TEXT FROM VOICE TYPING]'.
- Boundary markers: The template uses double quotes to wrap the dictated text but lacks specific instructions to the model to ignore any instructions embedded within that text.
- Capability inventory: The skill is purely for text generation and lacks capabilities to write files, execute commands, or access the network.
- Sanitization: No sanitization or input filtering is performed on the dictated text before it is processed.
Audit Metadata