The Agent Skills Directory

[PROMPT_INJECTION]: No attempts to override system instructions, bypass safety filters, or extract system prompts were detected in the skill instructions or metadata.
[DATA_EXFILTRATION]: The skill does not access sensitive local files (e.g., SSH keys, credentials) or perform unauthorized network requests. Mentions of database connections are restricted to architectural comments and templates.
[EXTERNAL_DOWNLOADS]: The skill references standard npm packages like fastify-plugin and provides links to the author's official GitHub repositories (mateonunez/fastify-orama, etc.). These are consistent with the skill's stated purpose and represent legitimate developer resources.
[REMOTE_CODE_EXECUTION]: No patterns for downloading and executing remote scripts or dynamic code evaluation (e.g., eval, exec) were found.
[OBFUSCATION]: The content is provided in plain text. No Base64 encoding, zero-width characters, homoglyphs, or other techniques to hide malicious intent were detected.
[COMMAND_EXECUTION]: No unauthorized shell command executions or privilege escalation attempts (e.g., sudo) were identified.
[SAFE]: The skill adheres to safe coding practices, including idempotency guards and proper TypeScript module augmentation, without introducing security risks.

fastify-plugin-shape