doubao-tts

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Interacts with ByteDance API endpoints at openspeech.bytedance.com to process speech synthesis requests and download generated audio files.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes arbitrary text input for synthesis, which serves as an ingestion point for potentially untrusted data that could influence agent behavior if not properly handled.
  • Ingestion points: The text parameter accepted by the execute methods of both TTSSelector and DoubaoTTS as shown in SKILL.md.
  • Boundary markers: None are defined; the skill does not use specific delimiters or instructions to ignore embedded commands within the text to be synthesized.
  • Capability inventory: The skill performs network communications to external servers (openspeech.bytedance.com) and writes files (audio and JSON metadata) to the local project environment.
  • Sanitization: No input validation, sanitization, or escaping mechanisms for the input text are described in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 12:01 AM