speech-to-text
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: The skill does not contain any malicious instructions, obfuscated code, or unauthorized data access patterns. All operations align with the stated purpose of audio transcription.
- [COMMAND_EXECUTION]: The skill uses the
infshCLI tool for its operations. This is the intended behavior for interacting with the inference.sh platform and is restricted to the specific CLI tool in the allowed-tools configuration. - [EXTERNAL_DOWNLOADS]: The documentation references adding related skills via
npxfrom theinference-shrepository. These are official vendor resources and do not pose a security risk in this context. - [PROMPT_INJECTION]: The skill ingests untrusted data via audio URLs for processing. This is a standard functional surface for transcription services, and the risk of indirect injection is considered low and managed by the underlying model's processing of audio content.
Audit Metadata