Security audit
Security checks for vulnerabilities and agentic risk
The skill appears to be a broad data-processing helper, but it requests read, write, glob, and command execution authority without clear limits or enforceable safeguards.
Review this skill before installing if you would use it on private datasets or important workspaces. Its data-processing purpose is plausible, but installation grants broad local file and command execution capabilities without clear boundaries; only use it where you are comfortable supervising file reads, writes, and commands yourself.
The skill declares exec capability and states that only whitelisted commands are executed, but no whitelist or enforcement mechanism is defined anywhere in the skill. In a skill with command execution, undocumented or nonexistent restrictions materially increase the risk of arbitrary command execution, misuse of user input, and unsafe file or system operations.
The invocation description is broad enough to match many generic data-related requests, which can cause the skill to activate in contexts the user did not specifically intend. Because the skill also advertises read/write/exec capabilities, overbroad triggering increases the chance of unnecessary access to files, data processing, or execution behavior beyond user expectations.
The skill describes execution, file access, and data handling capabilities, but it does not provide a prominent user-facing warning that these actions may affect local files, system state, or sensitive data. Without clear notice and consent boundaries, users may invoke the skill without understanding that it can read, write, or execute operations with real impact.
The skill claims encrypted transmission and encrypted storage, but the file is only Markdown metadata/instructions and contains no implementation or configuration that would enforce those protections. This creates a false sense of security for users who may provide sensitive data under incorrect assumptions, increasing the risk of mishandling or disclosure.
The description explicitly states '支持中文交互' while the document does not clearly offer a language choice or describe this as an optional capability. This can be interpreted as a locale/language preference baked into the skill rather than a user-selectable option.
