ppt-generator

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill performs a legitimate task of text-to-HTML conversion.
  • [EXTERNAL_DOWNLOADS]: The skill references assets from well-known and reputable CDNs.
  • Fetches the TailwindCSS library from ByteDance's public CDN (lf26-cdn-tos.bytecdntp.com).
  • Loads fonts from established mirrors such as Bilibili's static asset domain (s1.hdslb.com) and the loli.net font service.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for processing untrusted user data (the speech script) into generated code.
  • Ingestion points: The user's input lecture/speech script is read in SKILL.md (Step 1).
  • Boundary markers: Not explicitly defined in the instructions.
  • Capability inventory: The skill only generates HTML code output and does not possess capabilities for subprocess execution, file system writes, or network requests.
  • Sanitization: While not explicitly defined, the multi-step "refinement" and "distillation" instructions (Steps 2 and 3) naturally involve the agent transforming and summarizing the content, which mitigates the risk of direct injection of malicious scripts into the final HTML output.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 01:01 PM
Security Audit — agent-trust-hub — ppt-generator