elevenlabs-dubbing
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires permission to execute the
infshCLI throughBash(infsh *). This enables the agent to utilize the full range of subcommands provided by the Inference.sh platform. - [EXTERNAL_DOWNLOADS]: The documentation provides links to remote installation scripts and utilizes
npxto download and install additional skills from GitHub (inference-sh/skills). - [PROMPT_INJECTION]: The skill has an indirect prompt injection surface. Ingestion points: External audio and video files are retrieved via user-supplied URLs in the
--inputJSON. Boundary markers: The prompt template lacks specific instructions to ignore malicious content or instructions embedded in the external media. Capability inventory: The skill can execute shell commands and perform network operations via the CLI tool. Sanitization: Media content is not validated or sanitized prior to processing.
Audit Metadata