elevenlabs-dubbing

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches setup instructions and additional components from the inference-sh organization's public GitHub repository, which is the official source for the tool's configuration.
  • [COMMAND_EXECUTION]: The skill uses the 'belt' command-line interface to perform authentication and execute dubbing tasks. The tool access is restricted via the frontmatter to only allow 'belt' commands, following the principle of least privilege.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external audio and video content provided via URL.
  • Ingestion points: The 'audio' field in the tool input receives remote URLs in SKILL.md.
  • Boundary markers: No explicit delimiters are used to separate user-provided content from instructions in the tool call.
  • Capability inventory: The skill utilizes the Bash tool to run CLI commands as defined in SKILL.md.
  • Sanitization: Input content is passed to the dubbing tool without specific preprocessing or sanitization steps mentioned in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 01:13 PM
Security Audit — agent-trust-hub — elevenlabs-dubbing