podcast-generation

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or security vulnerabilities were detected in the skill's instructions or Python implementation code.
  • [EXTERNAL_DOWNLOADS]: The skill makes network requests to openspeech.bytedance.com for text-to-speech synthesis. This endpoint is a legitimate service owned by the skill's author (ByteDance) and is necessary for the skill's primary function.
  • [COMMAND_EXECUTION]: The skill executes an internal Python script (generate.py) to process audio and generate transcripts. The execution is scoped to the skill's directory and follows the described workflow.
  • [CREDENTIALS_UNSAFE]: Sensitive authentication tokens (VOLCENGINE_TTS_ACCESS_TOKEN) are managed via environment variables, which is the standard and recommended practice for secret management in this environment.
  • [PROMPT_INJECTION]: The skill converts user-provided text into podcast scripts, presenting a standard surface for indirect prompt injection. This is a functional requirement for the skill's primary purpose.
  • Ingestion points: User-provided text content converted to script JSON in SKILL.md.
  • Boundary markers: Data is structured into a specific JSON schema before processing.
  • Capability inventory: The generate.py script performs network requests (TTS API) and file writes (MP3 and Markdown outputs).
  • Sanitization: No explicit sanitization of input text is mentioned, relying on the agent's internal safety guardrails during script generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 01:16 PM