The Agent Skills Directory

[SAFE]: The skill was analyzed across all threat categories, including prompt injection, data exfiltration, and remote code execution. No malicious patterns or security vulnerabilities were identified. The instructions prioritize compliance with FTC regulations and platform terms of service. While the skill processes external data (creator posts and comments), this is intrinsic to its primary purpose of influencer vetting, and the skill does not possess high-privilege capabilities that would make it a significant target for indirect prompt injection.

influencer-marketing