better-icons

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the better-icons package globally using npm or bun. This external package provides the core CLI and MCP functionality.
  • [COMMAND_EXECUTION]: The skill uses a set of CLI commands (better-icons search, better-icons get, better-icons setup) to interact with the environment and search for icons.
  • [DATA_EXFILTRATION]: The sync_icon tool and search redirection examples involve writing content to the filesystem. Specifically, sync_icon accepts an absolute file path (icons_file) as an argument for icon placement.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing external data with file-system capabilities.
  • Ingestion points: Data is ingested from the Iconify API (api.iconify.design) whenever icon searches or retrievals are performed. (SKILL.md)
  • Boundary markers: No specific delimiters or instructions are provided to the agent to treat retrieved icon metadata as untrusted content.
  • Capability inventory: The skill possesses file-writing capabilities through the sync_icon tool and shell redirection commands. (SKILL.md)
  • Sanitization: The instructions do not mention sanitization or validation of the data fetched from the external API before it is processed or written to files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 12:57 AM
Security Audit — agent-trust-hub — better-icons