skills/mxyhi/ok-skills/better-icons/Gen Agent Trust Hub

better-icons

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill defines a command-line utility called better-icons that allows users to search, retrieve, and download SVG icons, and also provides a setup command to configure AI agent environments like Cursor and Claude Code.\n- [EXTERNAL_DOWNLOADS]: The skill references and fetches icon data from api.iconify.design, which is a well-known and reputable service for open-source icon sets.\n- [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection due to its handling of untrusted input and file system capabilities.\n
  • Ingestion points: Tools such as search_icons and recommend_icons take natural language input (query and use_case) which could contain malicious instructions.\n
  • Boundary markers: There are no documented boundary markers or instructions to the agent to disregard instructions embedded within the retrieved icon metadata or search results.\n
  • Capability inventory: The sync_icon tool can write to absolute file paths provided in the icons_file argument, and the CLI search command includes a download flag that writes to the local file system.\n
  • Sanitization: No explicit sanitization or validation of the input strings or the data retrieved from the external API is mentioned before these are used in file-writing operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 02:00 AM