Security audit
Security checks for vulnerabilities and agentic risk
This skill helps prepare product directory listings and does not install code, persist, or perform submissions automatically.
Before installing, be aware that the skill may read your project-context file and may use web search to fill product details. For confidential or unreleased products, ask the agent to avoid web searches or provide the needed details manually.
The trigger list is unusually broad and includes many common marketing phrases, which can cause the skill to activate for general requests not specifically about directory submission. Over-broad activation increases the chance the agent follows this skill's file-reading and web-search behaviors in contexts where the user did not clearly request them.
The skill instructs the agent to read local project-context files automatically, but does not require notifying the user or obtaining consent before accessing workspace files. This can expose sensitive internal product, business, or operational information beyond what the user expected to share in a simple content-generation request.
The skill directs the agent to search the web for pricing, competitors, and reviews when context is missing, without warning the user that external network requests may occur. This may leak the user's product interest or unreleased project details to third parties and can surprise users who expected an offline-only interaction.
No suspicious patterns detected.
