Security audit
Security checks for vulnerabilities and agentic risk
This looks like a Java coding guide, but it asks for command and write authority and gives broad automation/deployment instructions that are not clearly scoped to a reference handbook.
Review before installing. Use this only as a Java standards/reference guide, and do not allow it to run commands, modify files, troubleshoot networks, or perform deployment actions unless the user explicitly requests that specific action. A safer version would remove write access, narrow or remove exec access, and limit triggers to Java coding standards, examples, and secure-coding guidance.
The top-level trigger description is broad enough to match many ordinary development, debugging, testing, and deployment requests. In an agent environment, this increases the chance of over-invocation, where the skill may be selected in situations beyond its intended purpose and combined with privileged tools unnecessarily.
The description states '支持中文交互', and the file consistently presents the skill as Chinese-interaction oriented without indicating that users may choose another language. This can violate language/locale policy expectations when no opt-in or justified locale restriction is provided.
The skill is presented as a Java development handbook, but these sections expand it into generic create/query/modify/delete, export, save, and runtime configuration operations. This capability inflation can mislead the agent into treating a passive reference skill as an operational tool, increasing the chance of unintended file or system actions when paired with write/exec permissions.
The activation condition lacks concrete boundaries and effectively says to use the skill for a wide range of development tasks. Ambiguous triggers are dangerous in autonomous or semi-autonomous systems because they let a high-permission skill activate in loosely related contexts, increasing misuse risk.
The trigger/use-case wording extends the skill into deployment and broad automation/troubleshooting contexts, which is inconsistent with a Java standards reference manual. Overbroad operational framing can cause the agent to invoke the skill in contexts where command execution or environmental changes are riskier and not user-expected.
The file claims to be a pure Markdown instruction skill with no extra API key needs, yet also describes MD+EXEC, API-related behavior, and command execution. These inconsistencies obscure the real trust boundary and can cause users or orchestrators to underestimate the risk of local command execution or external interactions.
The skill describes command execution capability but does not present a prominent warning about system-impacting behavior, despite also advertising applicability in broad development workflows. In context, this is more dangerous because the skill has exec/write exposure while presenting itself mainly as a harmless handbook, making users less likely to anticipate side effects.
The error-handling table instructs users to run network connectivity and firewall/proxy troubleshooting steps even though the skill is positioned as a Java standards handbook. This injects unrelated operational behavior that could prompt unnecessary command execution or environment probing outside the skill's legitimate scope.
No suspicious patterns detected.
