Security audit
Security checks for vulnerabilities and agentic risk
This skill appears to be a local, template-based influencer outreach helper with no network access, persistence, credential use, or hidden high-impact behavior.
Before installing, be aware that the skill may activate on broad marketing terms like "creator" or "outreach". Its recommendations are heuristic and should be manually checked before contacting creators or making campaign decisions.
The manifest activates on single-word keywords such as "creator" and "outreach" without any contextual constraints or exclusion conditions. These terms are broad enough to match many ordinary conversations, making unintended invocation more likely.
The manifest sets "language": "en" and does not mention any user opt-in, alternative language support, or justification for an English-only constraint. Under the policy, forcing a specific language without user choice is a natural-language policy concern.
This code file contains a natural-language string in Chinese as part of its test input. Under the language/locale policy rule, hard-coding a specific language without any opt-in or documented justification can indicate an implicit locale preference.
No suspicious patterns detected.
