skills/ma1orek/replay/marp-slide/Gen Agent Trust Hub

marp-slide

Pass

Audited by Gen Agent Trust Hub on Sep 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The slide templates provided in the assets/ directory (e.g., template-basic.md) use @import to fetch fonts from Google Fonts (fonts.googleapis.com), which is a standard and well-known service for web resources.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text to populate presentation templates, which represents a surface for indirect prompt injection.
  • Ingestion points: User-provided content for slide titles, topics, and bullet points as described in the SKILL.md workflow.
  • Boundary markers: The generated Markdown files do not employ specific boundary delimiters to isolate user-supplied strings from the Marp directives or CSS structure.
  • Capability inventory: The skill is permitted to read local template files and write the generated Markdown output to the designated /mnt/user-data/outputs/ directory.
  • Sanitization: There is no explicit sanitization or filtering mechanism described for the user-supplied content prior to its inclusion in the generated slides.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 26, 2026, 11:45 AM