binance-leaderboard

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @binance/agentic-wallet npm package, which is a trusted resource published by the vendor for interacting with Binance Web3 services.
  • [COMMAND_EXECUTION]: The skill invokes subcommands of the baw CLI to perform wallet analysis and leaderboard queries, which are necessary for the skill's primary functionality and are scoped to the vendor's own tools.
  • [PROMPT_INJECTION]: The skill processes external blockchain data such as address labels and tags, which represents a standard surface for indirect prompt injection. 1. Ingestion points: Data retrieved through the baw leaderboard query, analyze, and alpha-radar commands. 2. Boundary markers: No explicit delimiters or boundary markers are defined for untrusted content in the display templates. 3. Capability inventory: The skill is restricted to network-based API requests via the official baw CLI. 4. Sanitization: The instructions do not specify any explicit validation or sanitization of data found in on-chain address metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 09:22 AM
Security Audit — agent-trust-hub — binance-leaderboard