The Agent Skills Directory

[SAFE]: The skill instructions and supporting files are focused exclusively on natural language translation and simplification. There are no functions for network communication, file system access, or command execution. The metadata and implementation details are consistent with the stated purpose. No evidence of malicious intent, data exfiltration, or unauthorized command execution was found.- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input and previous conversation turns to generate explanations, representing a standard indirect prompt injection surface for text-to-text assistants. However, the lack of dangerous capabilities mitigates this surface. • Ingestion points: Technical text provided by the user and preceding conversation turns. • Boundary markers: The instructions lack explicit structural delimiters for separating untrusted source text. • Capability inventory: The skill possesses no capabilities for external communication, file system access, or system command execution. • Sanitization: No specific input sanitization is defined.

plain-speak