The Agent Skills Directory

[CREDENTIALS_UNSAFE]: The skill follows security best practices by instructing users to manage sensitive data such as the DEPLOYER_PRIVATE_KEY via a .env file and explicitly directs the agent never to ask for the actual key.
[COMMAND_EXECUTION]: The skill utilizes the Bash tool to run local deployment scripts and the npx hardhat command. These operations involve processing user-provided inputs such as RPC URLs and git tags.
[SAFE]: The skill uses well-known development tools and official smart contract addresses associated with the vendor. No patterns of data exfiltration, obfuscation, or unauthorized persistence were detected.

upgrade-l2