skills/html2png/skills/og-image/Gen Agent Trust Hub

og-image

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes external resources from well-known content delivery networks and services.
  • Fetches styling libraries from cdn.tailwindcss.com.
  • Loads icons from unpkg.com via the Lucide library.
  • Retrieves typography from fonts.googleapis.com.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it interpolates HTML content that may originate from untrusted user or external data into a request body.
  • Ingestion points: The HTML payload passed to the https://html2png.dev/api/convert endpoint (found in SKILL.md).
  • Boundary markers: None present to delimit user-provided content from the HTML structure.
  • Capability inventory: Performs network POST requests to an external API service for image rendering.
  • Sanitization: No HTML sanitization or escaping mechanisms are specified in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 01:17 PM