speech-to-text
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references and links to resources from the inference.sh platform and its associated GitHub repository (github.com/inference-sh), which is required for its stated functionality.
- [COMMAND_EXECUTION]: The instructions direct the agent to use the Bash tool to execute belt CLI commands and suggest installing the belt-sh/cli package via npx.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes external, untrusted audio and video content. Malicious instructions spoken within the audio could potentially influence the agent if the transcribed output is used to drive subsequent actions without validation. Ingestion points: audio_url and video_url parameters in the CLI input. Boundary markers: None identified in the provided skill instructions. Capability inventory: Uses the Bash tool to run transcription models which output text to the agent's context. Sanitization: No sanitization or filtering of the transcribed text is specified.
Audit Metadata