Security audit
Security checks for vulnerabilities and agentic risk
This interview-prep skill is purpose-aligned and disclosed, with only a low-risk concern that its activation wording is broader than ideal.
Install this if you want an agent to use web research, read job-description files you provide, and save interview-prep guides. Avoid giving it sensitive personal files unless they are needed for the preparation task, and expect it may activate on broad interview-prep requests.
The activation description is broad enough to trigger on many generic interview-related requests, not just cases where the user has supplied a job description and company context. This can cause the agent to invoke external research tools unnecessarily, increasing the chance of oversharing user data, performing unintended web lookups, or bypassing a more appropriate narrower skill.
The 'When to Use' section uses ambiguous phrases like 'mentions interview preparation' and 'asks about what to study for a specific interview' without guardrails. In a tool-enabled skill that can perform web searches and read/write files, ambiguous routing broadens access to tools and can lead to unnecessary data handling or incorrect skill invocation.
The skill description contains broad mandatory trigger language such as 'Make sure to use this skill whenever the user asks about interview prep' and similar phrases tied to common topics. This can cause over-invocation outside narrowly intended contexts, increasing the chance that the agent unnecessarily uses powerful tools like web-search, read, and write on user inputs that only loosely match the domain.
No suspicious patterns detected.
