Security audit
Security checks for vulnerabilities and agentic risk
This macro-research skill is mostly purpose-aligned, but it asks the agent to fetch, update, and run unpinned external code that can use a local Cue API key.
Review this skill before installing if you are not comfortable with an agent cloning or updating external code under ~/.cue and running it locally. Use it only in an environment where the Cue API key in ~/.cue/config.json is intended for this service, and consider pinning or reviewing the cue-skills repository before execution.
The '何时用' section says only '全球宏观：宏观与日历', which does not clearly define when this skill should or should not be invoked. It lacks specific trigger phrases, scope boundaries, or negative examples, making invocation criteria too broad for a manifest/markdown skill description.
The skill instructs the agent to perform local shell actions that clone or update a remote repository and then execute a Python script from it. That expands the skill from data research into arbitrary code acquisition and execution, creating supply-chain and local-environment risk if the repository, mirror, or transport path is compromised.
The skill states that the runner automatically reads an API key from a local config file, which introduces credential access behavior not clearly disclosed in the skill’s stated purpose. Even if intended for convenience, directing an agent toward local credential material increases the chance of unintended secret exposure or use beyond user awareness.
The file presents all user-facing instructions and usage guidance in Chinese, but does not indicate that language is optional or limited to a Chinese-speaking audience for a documented reason. This can violate language/locale policy when a skill effectively forces one language without user opt-in.
