marp-slide
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data to generate slide decks, creating an inherent attack surface where untrusted data is interpolated into Markdown templates.\n
- Ingestion points: User-provided text, notes, or instructions used as source material for slides.\n
- Boundary markers: Absent; instructions do not specify the use of delimiters or 'ignore' directives for processed data.\n
- Capability inventory: The skill is authorized to write Markdown files to the '/mnt/user-data/outputs/' directory. It does not utilize network operations or shell execution tools.\n
- Sanitization: No explicit validation or sanitization of the input content is implemented.\n- [EXTERNAL_DOWNLOADS]: The skill's CSS templates reference font resources from 'fonts.googleapis.com'. This is a standard and safe practice for web-based styling using a trusted external service.
Audit Metadata