better-icons
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
better-iconspackage globally using standard package managers likenpmorbunto enable its CLI and MCP server capabilities.\n- [COMMAND_EXECUTION]: The skill relies on executing thebetter-iconsCLI tool to perform search, retrieval, and setup operations within the environment.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes content from the external Iconify API (api.iconify.design) and provides tools to write this content into project files, creating a potential vector for indirect prompt injection through untrusted data.\n - Ingestion points: Data is retrieved from the external endpoint
api.iconify.design.\n - Boundary markers: The instructions do not specify any delimiters or warnings to ignore instructions embedded in the icon metadata or SVG content.\n
- Capability inventory: Includes file-writing capabilities via the
sync_icontool and command execution via thebetter-iconsCLI.\n - Sanitization: No explicit sanitization or validation of the fetched API content is described in the skill instructions.
Audit Metadata