Security audit
Security checks for vulnerabilities and agentic risk
This is a plain Markdown workflow for producing competitor analysis reports, with no executable code, persistence, credential use, or hidden data movement.
Use this skill for competitor-analysis tasks where public web research is appropriate. Be careful not to share confidential business data through the off-platform WeChat contact, and verify important market or financial claims against authoritative sources before relying on the report.
The trigger list is very broad and overlaps with common business-analysis requests, increasing the chance that the skill activates in contexts beyond its intended scope. Overbroad activation can cause the agent to apply this workflow when a narrower or safer skill would be more appropriate, leading to prompt hijacking of task routing and unnecessary web collection behavior.
The activation conditions are phrased broadly enough to capture general strategy, investment, and market-opportunity work without clear limits. In a multi-skill agent, this can cause inappropriate invocation, over-collection from external sources, and cross-domain interference with other analysis skills better suited to the request.
The skill includes off-platform contact details and a solicitation for custom services that are unrelated to the core competitor-analysis workflow. This creates an unnecessary trust boundary bypass: users may be redirected outside the monitored agent environment, where data handling, logging, and safety controls no longer apply.
No suspicious patterns detected.
