The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external text provided by users, which represents a potential attack surface for indirect prompt injection. However, it mitigates this risk by including a specific directive to treat input manuscripts strictly as data and to ignore any embedded commands or role-play instructions.
[SAFE]: The skill performs only text analysis and modification tasks. It does not contain hardcoded credentials, network exfiltration patterns, or unauthorized system commands.

writing-ai-check