marp-slide
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified. The skill is designed for document generation and follows standard instructional practices for AI agents.
- [EXTERNAL_DOWNLOADS]: The skill templates include CSS imports for Google Fonts (
fonts.googleapis.com). This is a common and safe practice for typography in web-based slide formats and targets a well-known, trusted service. - [INDIRECT_PROMPT_INJECTION]: While the skill ingests user content to structure slides, it lacks high-privilege capabilities such as arbitrary shell execution or unauthorized network access, mitigating the risks typically associated with indirect prompt injection in content-processing tasks.
- [COMMAND_EXECUTION]: The documentation mentions Marp CLI commands and GitHub Action workflows as reference material for the user. The skill itself does not attempt to execute these commands or install untrusted software on the agent's host environment.
Audit Metadata