Security audit
Security checks for vulnerabilities and agentic risk
This is a broad coding-workflow skill that asks for normal workspace editing and command execution abilities, with no evidence of hidden, persistent, destructive, or exfiltrating behavior.
Install this only if you want a broad coding-process skill that can shape specs, implementation, testing, review, and release workflows. Use it in a bounded workspace and review actions before running commands, committing changes, or modifying project files.
The natural-language description and trigger wording are presented only in Chinese, which implies a language-specific interaction mode. There is no statement that users may choose another language or that the skill is intentionally limited to a Chinese-only regional or compliance context.
The trigger phrases are extremely broad and cover common software-development requests such as writing code, fixing bugs, code review, and testing. In agent ecosystems, this can cause the skill to activate in many unrelated contexts, unexpectedly injecting its own workflow, permissions, and behavioral rules into ordinary sessions, which increases the risk of mis-scoped execution and unsafe tool use.
No suspicious patterns detected.
