skills/nousresearch/hermes-agent/base/Gen Agent Trust Hub

base

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs read-only operations on the Base blockchain and fetches pricing data from CoinGecko. Both are well-known and legitimate services.
  • [SAFE]: No external dependencies are used; the helper script relies entirely on Python's standard library (urllib, json, argparse), which minimizes the attack surface and prevents supply chain risks.
  • [SAFE]: There is no evidence of credential exfiltration. The tool does not require API keys or access to sensitive local files (like .env or SSH keys).
  • [SAFE]: No obfuscation or hidden execution patterns were found. Cryptographic constants used (hashes and selectors) are standard for EVM-compatible blockchain interactions.
  • [SAFE]: The skill does not possess capabilities that could be exploited for indirect prompt injection, such as file-system writes or command execution. It primarily formats on-chain data into JSON for the agent's consumption.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 05:50 PM