Security audit
Security checks for vulnerabilities and agentic risk
This is a simple academic research guidance skill with overly broad activation phrases but no evidence of unsafe code, data access, persistence, or hidden behavior.
This appears safe to install for academic research assistance. The main thing to review is whether you want such broad triggers enabled; narrowing them to the exact skill name would reduce accidental activation.
The trigger field includes very broad terms such as "Academic," "Research," and especially "Skills," which are common words likely to appear in many unrelated conversations. This can cause unintended invocation of the skill, leading the agent to activate outside the user's actual intent and potentially override more appropriate routing or context-specific safeguards.
The natural-language trigger scenarios are overly broad, including generic phrases like users saying "Academic" or needing related help, which can match many benign requests unrelated to this skill. In a routing system, this increases the chance of accidental activation, misclassification of user intent, and inappropriate handling of requests that should be served by other skills or general assistance.
