Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed helper for turning completed work into reusable skills, with file creation gated on user confirmation.
Install this if you want the agent to notice reusable workflows and offer to turn them into skills. Expect occasional end-of-task prompts and review any generated skill before using it, since generated skills can influence future agent behavior.
The skill body is written as instructions in Chinese and does not state that language choice depends on user preference or context. This can violate language/locale policy when the user has not opted into Chinese or when the skill is used in multilingual environments.
The trigger conditions are very broad and instruct the agent to scan every conversation turn for reusable work, which can cause the skill to activate in many normal interactions without strong user intent. This creates prompt-injection and policy-drift risk by making the skill opportunistically steer conversations toward file creation and follow-up actions beyond the user's immediate request.
