md2video-audio
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute several local Python scripts (
ai-2md2marp2av.py,md2marp2av.py, andmd2video.py) to perform its core functions of rendering slides and generating video. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted content from user-provided Markdown documents which are then processed by the AI to generate narration and slides.
- Ingestion points: User-supplied Markdown files (e.g.,
tutorial.md) processed in Step 2 and Step 3. - Boundary markers: The instructions do not specify any delimiters or safety warnings to ignore instructions embedded within the source Markdown files.
- Capability inventory: The skill has the capability to write new files to the filesystem and execute shell-level Python commands.
- Sanitization: There is no evidence of content sanitization or filtering before the input data is used to generate secondary Markdown files or narrations.
Audit Metadata