carousel-designer

Pass

Audited by Gen Agent Trust Hub on Apr 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified in the skill code or instructions. The workflow correctly implements its stated functionality using standard tools.\n- [COMMAND_EXECUTION]: The skill executes a local Node.js script to perform browser-based rendering via Playwright. This command execution is necessary for the core task of generating image and PDF outputs.\n- [EXTERNAL_DOWNLOADS]: Fetches styling and typography from well-known and trusted services, specifically the Tailwind CSS CDN and Google Fonts. These are standard frontend assets used as documented.\n- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface due to processing user-provided data from references/REFERENCES.md.\n
  • Ingestion points: references/REFERENCES.md is read to extract design patterns.\n
  • Boundary markers: Absent; there are no delimiters or instructions to ignore embedded commands in the user-provided text.\n
  • Capability inventory: The skill can perform file-system writes (src/slides.html) and execute browser automation scripts (scripts/render.mjs).\n
  • Sanitization: Absent; no validation or filtering is applied to the content extracted from the references file. This risk is inherent to the primary purpose of the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 17, 2026, 10:29 AM