elevenlabs-dubbing

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs dubbing operations by executing the belt CLI tool. The execution environment is secured through frontmatter configuration that limits the Bash tool to only permit commands starting with belt, preventing arbitrary command execution.
  • [EXTERNAL_DOWNLOADS]: The skill references external dependencies and installation guides from GitHub repositories and package registries associated with the inference.sh platform. These downloads are necessary for the tool's operation and follow standard integration patterns for the ecosystem.
  • [PROMPT_INJECTION]: The skill processes external media files provided via URLs, which presents a surface for indirect prompt injection where instructions embedded in media could attempt to influence agent behavior. (1) Ingestion points: audio and video_url parameters in SKILL.md. (2) Boundary markers: Not present. (3) Capability inventory: belt CLI via restricted Bash tool. (4) Sanitization: None performed on external content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 10:40 PM
Security Audit — agent-trust-hub — elevenlabs-dubbing