html-ppt-retro-quarterly-review
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to read and process an external
DESIGN.mdfile to update visual styles. - Ingestion points: Reads instructions and style tokens from
DESIGN.md(SKILL.md, Workflow Step 1). - Boundary markers: None identified in the instructions for separating untrusted data in
DESIGN.mdfrom the core agent instructions. - Capability inventory: The skill requires
file_writecapability to emit the final HTML artifact. - Sanitization: No explicit sanitization or validation logic is defined for the content ingested from the external design file.
- [EXTERNAL_DOWNLOADS]: The generated HTML presentation templates reference external assets from well-known service providers.
- Fetches typography assets from Google Fonts (
fonts.googleapis.comandfonts.gstatic.com). - Loads the GSAP animation library from the JSDelivr content delivery network (
cdn.jsdelivr.net).
Audit Metadata