skills/qu-skills/skills/ai-podcast/Gen Agent Trust Hub

ai-podcast

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection vulnerability surface as it ingests untrusted user data into tools with significant execution capabilities. \n
  • Ingestion points: Character descriptions, script dialogue, and image URLs are provided by the user and processed by tools such as phota/train and inworld/text-to-speech-2. \n
  • Boundary markers: No specific delimiters or safety instructions are used to separate user data from the instructions provided to the AI models. \n
  • Capability inventory: The skill utilizes the Bash tool to execute system commands and has Write access to the local file system. \n
  • Sanitization: There is no evidence of validation or escaping for user-provided strings before they are interpolated into shell commands. \n- [COMMAND_EXECUTION]: Uses the Bash tool to execute the infsh CLI for managing media generation services. These operations are core to the skill's purpose and are documented in the app reference. \n- [EXTERNAL_DOWNLOADS]: The skill references and fetches external image and audio assets from user-provided URLs and remote services to facilitate the media creation pipeline.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 10:27 PM
Security Audit — agent-trust-hub — ai-podcast