The Agent Skills Directory

[SAFE]: The skill operates entirely as a set of text-based instructions and references. It does not invoke shell commands, perform network operations, or request access to sensitive local files beyond a provided business context file.
[PROMPT_INJECTION]: No malicious prompt injection patterns, such as attempts to override safety filters or extract system prompts, were detected. The instructions are focused on guiding the AI to generate marketing copy.
[DATA_EXFILTRATION]: No patterns associated with data exfiltration were found. The skill requests business context relevant to its primary function (target audience, CTAs, and pricing) and handles proof through placeholders rather than requesting real credentials or PII.
[OBFUSCATION]: The skill does not use base64, hex encoding, zero-width characters, or homoglyphs to hide malicious intent. The text is clear and readable across all referenced files.
[EXTERNAL_DOWNLOADS]: The skill does not perform any external downloads or install third-party packages. It relies on internal reference files and established marketing principles.

lead-offer