The Agent Skills Directory

[NO_CODE]: The skill consists entirely of markdown instructions and does not include any executable scripts, Python packages, or Node.js dependencies.
[SAFE]: The skill's primary function is to transform internal data points (scores and flags) into natural language explanations. It explicitly includes a safety instruction to never include biometric data in the explanations, limiting the scope to categorical data and numerical scores.
[SAFE]: No credential exposure, remote code execution, or data exfiltration patterns were detected. The skill does not interact with the file system or external network services.
[PROMPT_INJECTION]: While the skill processes data from other agents (an ingestion surface for indirect prompt injection), the risk is negligible as the skill only performs text summarization and does not have the capability to execute commands or perform sensitive operations based on that data.

decision_explainer