The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided concepts, formulas, and principles as input for explanation. This creates a surface for indirect prompt injection if the user-supplied content contains hidden instructions. However, the skill instructions focus exclusively on text generation and pedagogical output, and explicitly state that the agent should not create notes, files, or call other skills unless requested. The lack of dangerous tool capabilities (like file writing or network requests) minimizes the risk.
[SAFE]: A thorough analysis of the skill's instructions and configuration found no evidence of malicious patterns, prompt injection attempts, credential harvesting, or unauthorized remote code execution. The instructions are focused on clear communication and educational standards.

ljg-explain