better-icons
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user or agent to download and install the
better-iconspackage from the public NPM registry usingnpm installorbun add. It also utilizesnpxandbunxfor remote code execution. - [COMMAND_EXECUTION]: Provides several tools that execute shell commands to search for and retrieve icons. The
better-icons setupcommand installs services on the local system. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from an external API (Iconify) and has high-privilege capabilities.
- Ingestion points: Data enters the agent's context through the
search_icons,list_collections, andrecommend_iconstools, which fetch results fromhttps://api.iconify.design. - Boundary markers: The instructions lack delimiters or system warnings to ignore embedded instructions within the icon metadata or search results.
- Capability inventory: The
SyncIcontool (SKILL.md) allows the agent to write to arbitrary absolute file paths (icons_file), and thebetter-icons setuptool can modify project or global configurations. - Sanitization: There is no evidence of validation or sanitization of the icon IDs or file paths before they are used in file-system operations.
Audit Metadata