The Agent Skills Directory

[PROMPT_INJECTION]: No attempts to override agent behavior or bypass safety guidelines were found. The 'LLM WORKFLOW' section contains standard meta-instructions for maintaining the skill's file structure and does not constitute an injection attack.
[DATA_EXFILTRATION]: No hardcoded credentials, sensitive file path access, or network exfiltration patterns were detected. Code examples use standard web APIs like fetch and localStorage for educational purposes with placeholder targets.
[EXTERNAL_DOWNLOADS]: No remote code execution or suspicious package installations were found. The skill includes a legitimate link to the official Svelte documentation.
[COMMAND_EXECUTION]: No dangerous shell commands, privilege escalation, or persistence mechanisms were identified. References to CLI tools are limited to internal validation instructions for the agent.
[OBFUSCATION]: The content is clear and readable. No hidden characters, encoded commands, or deceptive text patterns were detected.
[SAFE]: The skill provides legitimate guidance for Svelte development and adheres to safety best practices.

svelte-runes