The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions designed to override agent behavior, bypass safety controls, or extract system prompts were found. The 'Instructions' and 'Guidelines' sections are standard functional guidance for the stated purpose.
[Data Exposure & Exfiltration] (SAFE): There are no hardcoded credentials, sensitive file paths, or network communication commands. The examples provided use generic data.
[Remote Code Execution] (SAFE): The skill contains no code or commands to download or execute remote scripts. It is a purely instructional document.
[Indirect Prompt Injection] (LOW): The skill processes user-provided data structures to output JSON schemas. However, because the skill lacks capabilities to write files, execute shell commands, or perform network requests, the risk associated with malicious data ingestion is negligible.
[Obfuscation] (SAFE): No hidden, encoded, or misleading content (Base64, homoglyphs, or zero-width characters) was detected in the text or metadata.

json-schema