The Agent Skills Directory

[PROMPT_INJECTION]: No evidence of prompt injection or instructions to bypass safety filters was found. The content is strictly technical and educational.
[DATA_EXFILTRATION]: No hardcoded credentials, sensitive file access, or suspicious network operations were detected. Code examples use placeholder data for illustrative purposes.
[REMOTE_CODE_EXECUTION]: There are no patterns suggesting the execution of remote scripts or arbitrary commands. The documentation refers to standard development practices within the TypeScript/Effect ecosystem.
[EXTERNAL_DOWNLOADS]: The skill mentions installing standard, well-known developer dependencies from official registries, specifically vitest and @effect/vitest via pnpm. These are standard tools for the described use case.
[COMMAND_EXECUTION]: No dangerous system commands or privilege escalation attempts were identified. All shell commands are related to standard package management.
[OBFUSCATION]: The content is clear and readable. No hidden characters, multi-layer encoding, or deceptive homoglyphs were found.
[INDIRECT_PROMPT_INJECTION]: The skill provides guidelines for the AI to follow when generating code. It does not ingest untrusted external data that could lead to indirect injection attacks.

testing