Skills
Navigate
skills/awesome-genmedia/skills/banner-ad-design/Gen Agent Trust Hub

banner-ad-design

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides examples of using the curl tool to make authenticated POST requests to the each::labs API endpoint at eachlabs.run.
  • [EXTERNAL_DOWNLOADS]: The skill interacts with external service endpoints (eachlabs.run) and links to official documentation at eachlabs.ai to facilitate its core functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill accepts user prompts and image URLs (e.g., brand assets) as inputs to generate banner ad creatives, creating a potential vector for indirect prompt injection.
  • Ingestion points: User-defined text prompts and image_url fields provided in documentation examples (SKILL.md).
  • Boundary markers: No explicit delimiter or framing instructions are provided in the examples to isolate external content.
  • Capability inventory: The skill utilizes Bash(curl) and WebFetch to transmit and retrieve data from external services.
  • Sanitization: The provided code examples do not include input validation or sanitization for the prompt content.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 05:21 AM