The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external Solidity code and test files through compilation and analysis tools, creating a potential surface for indirect injection if the source code contains malicious instructions.
Ingestion points: Solidity contracts (.sol) and test files (.t.sol, .ts) processed by the agent.
Boundary markers: The skill does not define specific prompt boundaries or "ignore instructions" delimiters for the ingested code.
Capability inventory: The skill utilizes MCP tools such as compile_contract, run_tests, and run_slither which execute shell commands to process the files.
Sanitization: Security depends on the isolation and sanitization provided by the underlying Hardhat and Slither toolchains.
[EXTERNAL_DOWNLOADS]: The skill references and imports official plugins from the Nomic Foundation (e.g., @nomicfoundation/hardhat-ignition, @nomicfoundation/hardhat-viem) and testing libraries like forge-std. These are well-known and trusted resources in the Ethereum development ecosystem.
[COMMAND_EXECUTION]: The skill provides instructions for standard development operations using the npx hardhat CLI, including project initialization, building, and running tests. These actions are appropriate for the skill's stated purpose of smart contract development.

solidity-hardhat-development