Security audit
Security checks for vulnerabilities and agentic risk
This skill only drafts B2B sales outreach copy and does not send messages, connect to accounts, install code, or persist anything.
Before installing, users should know this is a drafting aid for sales outreach only. Review generated copy before use and follow applicable anti-spam and privacy laws; the artifact itself says it does not send emails or connect to outreach platforms.
The skill explicitly instructs broad activation for 'any task involving outbound messaging' and even casual phrasing, which can cause the agent to invoke this skill outside the user's actual intent. In a sales-copy skill, over-triggering is risky because it can steer unrelated conversations into persuasive outbound-content generation and override more appropriate, narrower skills.
The trigger examples include ambiguous phrases such as 'help me reach out' and 'write a follow-up' without requiring clear sales or prospecting context. This makes accidental activation more likely, which can misroute user requests and bias the model toward outreach behavior even when the user meant a different type of communication.
The metadata sets 'language: en', and the file does not indicate that users may opt into other languages or that English-only behavior is required for a documented regional purpose. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.
No suspicious patterns detected.
