The Agent Skills Directory

[Prompt Injection] (SAFE): The analyzed files contain no instructions intended to override agent behavior, bypass safety filters, or extract system prompts. The content is strictly technical documentation for software development.- [Data Exposure & Exfiltration] (SAFE): While the code snippets demonstrate how to handle authentication tokens (JWT) and perform cryptographic signing, these are presented as implementation patterns for a wallet/ledger application. No hardcoded credentials, sensitive file path access, or exfiltration logic were found.- [Unverifiable Dependencies & Remote Code Execution] (SAFE): The documentation references standard .NET libraries (System.CommandLine, Refit, Moq, FluentAssertions) and internal project references. There are no patterns involving the download and execution of remote scripts or unverified third-party packages.- [Obfuscation] (SAFE): No evidence of encoded commands, zero-width characters, or homoglyphs designed to hide malicious intent was identified. Base64 usage is limited to standard cryptographic and data transmission patterns in the provided C# snippets.

sorcha-cli