Skills
Navigate
skills/awesome-genmedia/skills/app-icon-design/Gen Agent Trust Hub

app-icon-design

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses WebFetch and provides examples of fetching images from external URLs (e.g., https://example.com/company-logo.png) to be used as design references.
  • [COMMAND_EXECUTION]: The skill utilizes the Bash(curl *) tool and provides multiple examples of executing curl commands to interact with the eachsense-agent.core.eachlabs.run API endpoint.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection through external data processing.
  • Ingestion points: Processes external images provided via URL in the image_url field of API requests (referenced in SKILL.md).
  • Boundary markers: None identified in the prompt templates to distinguish between design instructions and potential malicious content embedded in reference images.
  • Capability inventory: Executes curl commands via the Bash tool to send data to external endpoints.
  • Sanitization: No sanitization or validation of the content fetched from external URLs is documented.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 05:21 AM