The Agent Skills Directory

[SAFE]: No security issues detected. The skill focuses on providing architectural guidance and templates for blockchain development and smart contract security.
[CREDENTIALS_UNSAFE]: The skill follows security best practices by explicitly instructing the agent to never suggest writing raw private keys to configuration files and recommending the use of Hardware Security Modules (HSMs) or secure enclaves.
[PROMPT_INJECTION]: No malicious instruction overrides, safety filter bypasses, or system prompt extraction patterns were found.
[REMOTE_CODE_EXECUTION]: No remote code execution patterns, untrusted downloads, or suspicious package installations were detected. The mentioned tools (Hardhat, Foundry, Ganache) are standard development environments for the stated purpose.
[DATA_EXFILTRATION]: No network operations or sensitive file access patterns were found that would indicate data exfiltration risks.
[INDIRECT_PROMPT_INJECTION]: The skill has no high-risk capabilities (like shell access or network requests) and does not ingest external untrusted data beyond standard user queries, posing no significant surface for indirect injection.

blockchain-dlt