Security audit
Security checks for vulnerabilities and agentic risk
This is a small debugging-process skill with no executable code, persistence, hidden data access, or privilege-seeking behavior.
Before installing, understand that this skill may activate in many troubleshooting situations and will nudge the agent toward a structured debugging workflow. It does not install code or request special access, but the publisher could improve clarity by narrowing the trigger and marking the non-English example as illustrative.
The skill description is broad enough to trigger in many ordinary troubleshooting contexts, which can cause the agent to invoke this skill when a more specific or safer skill would be more appropriate. Over-broad activation increases the chance of prompt-scope hijacking, unintended precedence over other skills, and unnecessary exposure to adversarial debugging content.
The reporting-style example is written in Korean, which can implicitly steer the skill toward a specific language despite no stated user preference or opt-in. The file does not explain that Korean is optional, illustrative only, or required for a justified regional context.
No suspicious patterns detected.
