Security audit
Security checks for vulnerabilities and agentic risk
This is a Chinese-language quant research team workflow skill with no executable code, persistence, credential use, or hidden data movement found.
Install this only if you want a Chinese-language quant research workflow. Confirm before using it for real trading, publishing, deployment, or regulated financial decisions, because the skill discusses those workflows but does not itself provide safety controls beyond role-based review steps.
The skill exposes multiple generic trigger phrases such as “公司架构”, “研究团队”, and “量化团队” in metadata/user-facing activation guidance. Broad, natural-language triggers increase the chance of accidental invocation during unrelated conversation, which can unexpectedly shift the assistant into this multi-agent workflow and potentially cause unintended task routing or disclosure of internal skill behavior.
The skill is written entirely in Chinese and presents commands/workflows only in Chinese, without documenting language negotiation or fallback behavior. This can cause user-intent mismatches, inaccessible operation for non-Chinese users, or accidental misuse if the platform expects multilingual interaction, though it is not directly a code-execution or privilege-escalation issue.
This JSON configuration defines the organization, agent names, and role descriptions entirely in Chinese, with no indication that language selection is optional or limited to a justified region-specific deployment. Under the policy, forcing a specific language or locale without user opt-in is a natural-language policy violation.
No suspicious patterns detected.
