Security audit
Security checks for vulnerabilities and agentic risk
The skill is a broad automation/agent skill with read, write, and command execution authority, but its scope and safety claims are too vague for that level of access.
Review this skill carefully before installing. It asks for broad file and command execution tools and should only be used in a constrained workspace where you are comfortable with file changes and command execution. Do not rely on its sandbox, whitelist, encryption, or permission-control claims unless the host platform separately enforces them.
The description says to use the skill whenever AI model calling, intelligent dialogue, agent orchestration, or LLM applications are needed, which covers a very wide range of common AI tasks. It does not provide specific trigger phrases, scope boundaries, or negative examples beyond one narrow exclusion, so it could overlap with many unrelated skills and cause unintended invocation.
The skill advertises that command execution occurs in a safe sandbox and under whitelist restrictions, but the manifest exposes broad exec capability and the markdown provides no enforceable constraints or implementation details. This can mislead users and host agents into trusting potentially dangerous command execution behavior that may have full system impact.
The skill describes file handling, API integration, and command execution capabilities without a prominent up-front warning that these actions can modify the filesystem, invoke external services, or affect the local environment. In a skill with read/write/exec tools, weak disclosure increases the risk of unsafe invocation and unintended system or data impact.
The display name, summary, and primary description are presented in Chinese, with no statement that users may choose their preferred language. For a general-purpose agent skill, this can amount to a locale/language policy issue unless the language restriction is explicit and justified.
The documentation claims encrypted communication and permission controls for protecting data, but the skill definition contains no evidence of these controls or any mechanism that would guarantee them. Unsupported security assurances create a false sense of safety and may cause users to expose sensitive data under incorrect assumptions.
No suspicious patterns detected.
