The Agent Skills Directory

[SAFE]: The skill content is strictly focused on cryptographic guidance and implementation security. No malicious code, prompt injection, or data exfiltration patterns were identified.- [EXTERNAL_DOWNLOADS]: The skill correctly references and provides implementation examples using standard libraries including libsecp256k1, blst, and ed25519-dalek. All external references are to well-known, trusted cryptographic repositories and standards.- [COMMAND_EXECUTION]: Shell command examples are limited to common development tools like circom and snarkjs. No suspicious or unnecessary command execution was detected in any of the skill files.- [DATA_EXFILTRATION]: The skill does not access sensitive system paths or credentials. It provides correct guidance on secret management, such as using BIP-32 for hierarchical deterministic key derivation.

blockchain-cryptography