The Agent Skills Directory

[SAFE]: The skill instructions and configuration files contain no malicious patterns, obfuscation, or unauthorized access attempts. The content is limited to architectural guidance and example code patterns for the Litestar framework.\n- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for processing user-supplied requirements into API contracts, which represents a potential ingestion surface for untrusted data. Evidence chain analysis:\n * Ingestion points: User requirements for API request/response modeling (SKILL.md).\n * Boundary markers: None present.\n * Capability inventory: No execution scripts, shell commands, or network operations are included in the skill.\n * Sanitization: No input sanitization or filtering logic is specified.

litestar-dataclasses