ios-icon-gen

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads icon assets in SVG format from https://api.iconify.design. This is a well-known and widely used service for open-source icon collections. The downloaded files are used as source material for image conversion and are not executed as code.
  • [COMMAND_EXECUTION]: The skill utilizes several local command-line tools to perform its tasks. It uses curl for fetching remote assets, sips (a built-in macOS utility) for converting SVG files to PNG, and python3 one-liners for URL encoding and JSON parsing of API responses. These operations are standard for the skill's stated purpose of icon generation.
  • [INDIRECT_PROMPT_INJECTION]: The skill fetches and displays search results and collection metadata from a remote API, which constitutes an indirect prompt injection surface.
  • Ingestion points: Icon search results and collection lists retrieved via scripts/iconify_gen.sh from the Iconify API.
  • Boundary markers: Not present. The agent processes the raw output from the shell script.
  • Capability inventory: The skill can write to the local filesystem (mkdir, sips, shell redirection) and perform network requests (curl).
  • Sanitization: The script employs Python's json module to parse API responses, ensuring that the structure is correctly handled, though the content itself is treated as trusted text by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 03:41 PM
Security Audit — agent-trust-hub — ios-icon-gen