design-system
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses Python scripts to wrap and call local utility tools via
subprocess.run. These implementations correctly use list-based arguments rather than shell strings, which effectively prevents shell injection vulnerabilities. - [INDIRECT_PROMPT_INJECTION]: The slide generation script (
generate-slide.py) processes user-supplied data to populate HTML templates. It mitigates potential injection risks (such as XSS) by implementing an evidence chain of protection: it ingests data through CLI/JSON, utilizeshtml.escapefor all interpolated content, restricts URL schemes to a safe allowlist, and lacks high-privilege capabilities like network-send or raw-exec on the processed data. - [EXTERNAL_DOWNLOADS]: The image fetching script (
fetch-background.py) references Pexels, a well-known service for high-quality stock photography. These plain-text URLs are used solely for slide background enrichment and do not involve executable code or untrusted third-party scripts.
Audit Metadata