muapi-seedance-2

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a bash script (scripts/generate-seedance.sh) to interact with an external API. This script executes standard tools like curl, jq, and python3 for network requests, JSON parsing, and string encoding. These are routine operations for an API wrapper skill.
  • [EXTERNAL_DOWNLOADS]: The skill downloads generated video/image content from api.muapi.ai and potentially user-provided URLs in video-edit and watermark-remove modes. These downloads are directed to a local media_outputs directory and are part of the intended functionality.
  • [DATA_EXFILTRATION]: The skill sends user-provided prompts, images, videos, and audio files to api.muapi.ai to perform AI generation tasks. This is the core purpose of the skill and follows standard API interaction patterns. The script requires an MUAPI_KEY for authentication, which is expected to be provided by the user via environment variables.
  • [SAFE]: No obfuscation, persistence mechanisms, privilege escalation, or malicious prompt injection patterns were detected. The script handles local file uploads securely by sending them to a dedicated upload endpoint before referencing them in generation tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 11:14 PM