The Agent Skills Directory

[Prompt Injection] (SAFE): The skill follows standard instructional formatting without attempting to override system constraints or extract system prompts.- [Data Exposure & Exfiltration] (SAFE): No hardcoded secrets, sensitive file paths, or unauthorized network operations were found in the skill or reference files.- [Obfuscation] (SAFE): The provided code snippets and validation rules are written in plain text with no use of Base64, zero-width characters, or other encoding techniques.- [Unverifiable Dependencies & Remote Code Execution] (SAFE): While Solidity code snippets include imports (e.g., @layerzerolabs), these are standard for technical reference materials and do not involve runtime execution or package installation commands like npm or pip.- [Persistence & Privilege Escalation] (SAFE): No commands related to system persistence or privilege modification were identified.- [Indirect Prompt Injection] (SAFE): The skill acts as a validator for external code (Surface Area), but it lacks any 'write' or 'execute' capabilities, mitigating the risk of downstream exploitation.

cross-chain