hyperframes-slide-work-kindergarten-notice

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses local command-line tools for linting content and serving a local preview during the development workflow.
  • Evidence: npx hyperframes lint topics/<주제> in SKILL.md.
  • Evidence: bash .codex/skills/hyperframes-overview/serve.sh topics/<주제> 8765 in SKILL.md.
  • [EXTERNAL_DOWNLOADS]: The skill references font styles and animation libraries from a well-known content delivery network.
  • Evidence: https://cdn.jsdelivr.net/gh/fonts-archive/Paperlogy/subsets/Paperlogy-dynamic-subset.css in assets/template.html.
  • Evidence: https://cdn.jsdelivr.net/npm/gsap@3.14.2/dist/gsap.min.js in assets/template.html.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted teacher-provided observations and educational content to populate HTML templates, creating a surface for potential injection if malicious content is processed.
  • Ingestion points: The agent populates .story-text and other placeholders with user-provided text as described in SKILL.md.
  • Boundary markers: Absent. The provided HTML snippets do not include explicit delimiters or sanitization warnings for interpolated content.
  • Capability inventory: The skill has the ability to execute shell commands (npx, bash) and client-side JavaScript (gsap).
  • Sanitization: Absent. The templates directly interpolate strings into HTML without visible escaping or validation logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 06:41 PM
Security Audit — agent-trust-hub — hyperframes-slide-work-kindergarten-notice