slide-deck

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches the reveal.js library, themes, and highlighting plugins from the JSDelivr CDN (cdn.jsdelivr.net). These are well-known and standard resources for this type of application.
  • [PROMPT_INJECTION]: The skill processes untrusted user data into HTML output. Evidence Chain: 1. Ingestion points: User-provided topics, markdown, and outlines in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Generates and writes HTML files to the local file system. 4. Sanitization: No sanitization of user-provided content is performed before interpolation.
  • [SAFE]: The skill does not contain any obfuscated code, credential harvesting mechanisms, or unauthorized network calls. Its operations are consistent with its described functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 10:02 AM
Security Audit — agent-trust-hub — slide-deck