The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were identified. The skill consists of documentation, code examples, and architectural guidance for the tinystruct Java framework.- [PROMPT_INJECTION]: The instructions do not contain any attempts to override safety protocols, bypass constraints, or extract system prompts. The language is purely instructional for development purposes.- [DATA_EXFILTRATION]: No sensitive file paths (e.g., credentials, SSH keys) or hardcoded secrets are present. The framework documentation uses standard placeholders for configuration examples.- [REMOTE_CODE_EXECUTION]: There are no patterns involving remote script downloads or execution. The skill describes internal Java framework mechanisms and CLI dispatching for local development.- [INDIRECT_PROMPT_INJECTION]: The skill documents surfaces where untrusted data enters the application context (Ingestion points: Request parameters, Context attributes, and URL segments in references/routing.md). It promotes safety through regex-based parameter matching (Boundary markers/Sanitization: @Action regex segments like \\d+). No dangerous capabilities (Capability inventory: File-writes, network ops) are exposed in the provided patterns.

tinystruct-patterns