Skills
Navigate
skills/inference-sh/skills/speech-to-text/Gen Agent Trust Hub

speech-to-text

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the belt CLI tool via the Bash tool to perform transcription and translation tasks.
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the belt-sh/cli package and references installation scripts hosted on GitHub under the inference-sh organization.
  • [DATA_EXFILTRATION]: The skill transmits audio URLs to the inference.sh platform for processing. This network operation is the core function of the skill for cloud-based inference.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection from transcribed audio content. 1. Ingestion points: External audio data provided via the audio_url parameter. 2. Boundary markers: Absent; the skill does not define delimiters to separate transcribed text from instructions. 3. Capability inventory: The agent has access to the Bash tool for running belt commands. 4. Sanitization: No sanitization or validation of the transcribed output is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 06:33 PM
Security Audit — agent-trust-hub — speech-to-text