marp-slide
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's CSS and template files (e.g.,
assets/theme-default.css,assets/template-basic.md) import font resources from Google Fonts (fonts.googleapis.com). This is a standard and safe practice for providing high-quality typography in presentations using a well-known service. - [INDIRECT_PROMPT_INJECTION]: The skill transforms user-provided content into presentation slides, which naturally involves processing untrusted data.
- Ingestion points: User content is ingested via prompts to generate slide titles, bullet points, and descriptions.
- Boundary markers: The skill instructions do not specify the use of boundary markers or delimiters when the agent processes user input for slide creation.
- Capability inventory: The skill's primary capability is writing Markdown files to the
/mnt/user-data/outputs/directory. It does not perform command execution, network requests for exfiltration, or sensitive file operations. - Sanitization: There are no explicit sanitization or validation steps for user-provided content, but the impact is limited to the visual display of the generated Markdown file.
Audit Metadata