speech-to-text
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides references to installation scripts and documentation hosted on the official GitHub repository and website for the inference.sh service.
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from remote audio and video URLs, which represents a potential surface for indirect prompt injection if the media contains malicious instructions.
- Ingestion points: Remote audio_url and video_url parameters in SKILL.md examples.
- Boundary markers: Absent.
- Capability inventory: Shell command execution through the belt CLI tool as specified in SKILL.md.
- Sanitization: Absent.
Audit Metadata