html-ppt-retro-quarterly-review
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-controlled data from
DESIGN.mdto interpolate values and logic into generated HTML/JavaScript artifacts, creating a surface for indirect prompt injection. - Ingestion points: The agent is instructed to read
DESIGN.mdto map token changes into CSS variables (Workflow Step 1). - Boundary markers: Absent; there are no specific delimiters or instructions to ignore embedded commands within the configuration file.
- Capability inventory: The skill utilizes
file_writeand generates interactive artifacts containing JavaScript logic. - Sanitization: Absent; while a checklist exists for functional P0s, there is no requirement for sanitizing or validating inputs from the design file before artifact generation.
- [EXTERNAL_DOWNLOADS]: The skill fetches resources from well-known and established technology providers.
- Evidence: References Google Fonts (
fonts.googleapis.com) and the GSAP animation library from the JSDelivr CDN (cdn.jsdelivr.net).
Audit Metadata