md2video-audio
Warn
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to run Python scripts (
ai-2md2marp2av.py,md2marp2av.py, andmd2video.py). Because these scripts are part of a community-sourced repository and their source code is not included in the provided skill definition for review, they could perform unverified operations on the user's system. - [INDIRECT_PROMPT_INJECTION]: The workflow involves the agent reading, reformatting, and generating content based on user-provided Markdown files. This creates a surface where an attacker could embed malicious instructions in a document that the agent then follows during the conversion process.
- Ingestion points: The source Markdown file provided by the user in Step 2.
- Boundary markers: The skill does not define specific delimiters or instructions to treat the input as untrustworthy text.
- Capability inventory: The skill can execute shell commands (
python), write new files to the system, and perform network requests (via theEdge-TTSdependency). - Sanitization: No sanitization or validation of the input Markdown content is specified.
Audit Metadata