elevenlabs-dialogue

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install dependencies from the inference-sh GitHub organization using the npx skills add command.
  • [EXTERNAL_DOWNLOADS]: The skill references a remote installation guide hosted at raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md.
  • [COMMAND_EXECUTION]: The skill requires the Bash tool with belt CLI access to perform authentication and run inference tasks.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted text data within the segments field to generate audio output. This is a potential injection surface, though the risk is minimized as the output is non-executable audio.
  • Ingestion points: The segments input in the belt app run command (found in SKILL.md).
  • Boundary markers: None; the text is passed as raw strings within a JSON structure.
  • Capability inventory: The skill utilizes the Bash tool to interact with the external belt CLI.
  • Sanitization: No explicit sanitization or filtering of the input text is performed before it is sent to the audio generation engine.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:20 PM
Security Audit — agent-trust-hub — elevenlabs-dialogue