crypto-token-screener

Pass

Audited by Gen Agent Trust Hub on Aug 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches real-time financial data from well-known and reputable services including CoinGecko (api.coingecko.com) and DefiLlama (api.llama.fi). These connections are necessary for the skill's primary purpose of screening crypto tokens.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data from public APIs. While this creates a theoretical surface for indirect injection (e.g., if an API provider's metadata was compromised), the tool primarily processes numeric financial data (market cap, revenue, price trends), and the results are presented in a structured report, significantly minimizing the risk of instructions being accidentally followed by the agent.
  • [COMMAND_EXECUTION]: The skill includes a local Python script scripts/screen.py to automate data collection. The script uses standard libraries and does not perform any dangerous system operations or privilege escalation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 20, 2026, 02:21 PM
Security Audit — agent-trust-hub — crypto-token-screener