Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed financial-analysis workflow that searches public market sources and writes a local report, with no evidence of hidden execution, credential access, persistence, or account-changing behavior.
Install only if you want an agent to perform web-based tender-offer research and create local Markdown reports. Verify all SEC filings, prices, deadlines, and brokerage requirements independently before making investment decisions, and avoid using it if you cannot comfortably read the Chinese report output.
The natural-language documentation and example invocation are entirely in Chinese, with no indication that other languages are supported or that the user can choose their preferred language. This can constitute a language/locale policy issue when a skill implicitly requires a specific language without opt-in.
The README tells users to invoke the skill with a single natural-language phrase, "扫描当前市场上的要约收购套利机会," but does not define alternate allowed triggers, exclusions, or contextual limits. This makes activation criteria somewhat open-ended and could lead to unintended invocation from similar market-scanning requests.
The skill mandates Chinese-only output without offering the user a language choice. While not a classic security flaw, it can reduce transparency and user comprehension, which is risky in a financial-analysis context because users may miss warnings, assumptions, or side effects if they do not read Chinese.
The file structure states that the agent-generated reports are saved under the results/ directory, which implies local file writes. The README does not explicitly warn users that running the skill will create or overwrite local analysis output files.
The skill explicitly instructs the agent to save a generated report to a local path, but it does not require prior user consent or a warning before writing to the filesystem. Unconsented file creation can have side effects in agent environments, especially if users expect analysis-only behavior or if automated execution writes into sensitive or persistent workspaces.
No suspicious patterns detected.
