Security audit
Security checks for vulnerabilities and agentic risk
This is a prompt-only academic topic-selection skill with no code execution, data access, persistence, or hidden side effects.
Before installing, understand that this skill may be invoked for broad academic research-topic brainstorming. It is low risk from a security perspective because it is prompt-only and does not access files, credentials, networks, or persistent state.
The skill description is framed so broadly that it can trigger on common requests like finding research directions or exploring ideas in nearly any domain. Over-broad activation increases the chance the skill hijacks general conversations and injects its prescribed workflow when the user did not explicitly ask for this specialized behavior.
The example trigger phrase is generic enough to overlap with ordinary academic-help requests, which can cause unintended invocation of the skill. In an agent setting, this kind of ambiguous trigger can degrade routing integrity and override better-matched skills or the base assistant behavior.
