Security audit
Security checks for vulnerabilities and agentic risk
This is a product-research prompt skill that asks the agent to gather public market, competitor, technical, and supply-chain information without hidden execution or privileged access.
Install this if you want a Chinese-oriented product research report format. Be aware that broad trigger phrases may make it activate for some general analysis requests, so check that the task is actually product or market research when it appears.
The description is written to strongly imply Chinese-first behavior, which can steer output language without checking the user's preference. While not a direct security exploit, it can override user intent and create unsafe assumptions in multi-lingual contexts where precise output control matters.
The trigger list contains very broad phrases such as "帮我分析" and "想做一款", which can match ordinary conversation unrelated to this skill. This can cause unintended activation, making the agent inject this skill's workflow and output format into unrelated tasks, which is a prompt-scope and routing problem even if it is not overtly malicious.
No suspicious patterns detected.
