mage-short-drama
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill connects to the Mage MCP server at
mcp.mage.spaceto utilize generative models for images, video, and audio. These interactions are limited to official vendor services required for the skill's primary function. - [COMMAND_EXECUTION]: The skill utilizes
ffmpegshell commands for local media processing, such as joining video clips and layering audio. These commands are generated based on local file paths and follow standard media editing practices. - [INDIRECT_PROMPT_INJECTION]: The skill handles untrusted user input (scripts and dialogue) to generate prompts for AI models. It employs specific structures and boundary markers, such as curly braces
{}for dialogue, to help downstream models distinguish between instructions and data. Capability inventory includes local file manipulation and Mage API interaction, with user scripts as the primary ingestion point.
Audit Metadata