The Agent Skills Directory

[Prompt Injection] (SAFE): The skill instructions do not contain any patterns intended to bypass AI safety filters, extract system prompts, or override agent behavior.- [Data Exposure & Exfiltration] (SAFE): No hardcoded secrets, sensitive file paths, or network exfiltration patterns were detected in the documentation.- [Obfuscation] (SAFE): The content is provided in plain text and does not use Base64, zero-width characters, or other encoding techniques to hide malicious intent.- [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill does not download or execute any external packages or scripts; it only provides structural guidance for code generation.- [Privilege Escalation] (SAFE): No commands related to acquiring elevated permissions or modifying system configurations are present.

code-generator