Security audit
Security checks for vulnerabilities and agentic risk
This is a simple documentation-only skill for mobile responsive layout help, with no hidden execution or sensitive access, though its triggers are overly broad.
Install only if you are comfortable with a broadly triggered mobile responsive layout helper. The main practical risk is accidental invocation on unrelated prompts mentioning generic words like mobile or fixes; there is no evidence of hidden code execution or sensitive data access.
The skill description is broad enough to activate on common terms like "mobile," "responsive," and "fixes," which can cause the agent to invoke this skill for loosely related requests. Over-broad routing increases the chance of irrelevant guidance, prompt-scope confusion, and accidental interception of tasks better handled by a different skill or baseline behavior.
The trigger keywords include highly generic terms such as "mobile," "fixes," "labels," "level," "beginner," and "type," which are likely to match many unrelated user prompts. This makes unintended skill activation substantially more likely, creating routing instability and increasing the risk that the skill overrides more appropriate instructions or produces off-target changes in broader workflows.
The trigger phrase is broad enough to match ordinary help-seeking language rather than a narrowly scoped invocation, which can cause this skill to activate in situations the user did not explicitly intend. In an agent environment, overly generic triggers increase the chance of incorrect routing or prompt shadowing, especially because this skill targets common terms like "mobile," "responsive," and "fixes."
The trigger phrases are broad and generic, including common terms like 'mobile', 'responsive', and 'fixes', which can cause the skill to activate in contexts far beyond the intended use. Over-broad activation increases the chance of unintended invocation, irrelevant guidance, or prompt-surface expansion when other user requests mention these common words.
This file is written as a Chinese README and labels companion files by language, but it does not state that language is optional or user-selectable. Under the policy, imposing a specific language or locale without opt-in can be a natural-language policy violation unless clearly justified.
The skill description uses broad activation terms such as creative-and-content, mobile, responsive, fixes, and labels without strong scope boundaries. This can cause the agent to invoke the skill in unrelated conversations, leading to inappropriate context capture, wrong actions, or overshadowing more suitable skills.
The keyword trigger list is overly broad and includes generic terms like mobile, fixes, level, beginner, and type, which are likely to appear in many unrelated requests. In an agent environment, this increases accidental skill routing and may result in irrelevant or unsafe automated assistance being prioritized over the correct workflow.
The default prompt uses a very broad invocation phrase, and the policy also allows implicit invocation. Together, this can cause the skill to trigger on common user requests about mobile, responsive, fixes, labels, workflows, or implementation support, even when the user did not intend to use this specific skill. That increases the risk of unintended routing, over-collection of user context, and execution of the wrong capability in normal conversations.
The trigger sentences are generic enough to match ordinary user requests like 'Help me Mobile Responsive Fixes' or requests for a 'practical workflow,' which can cause the skill to activate outside its intended scope. Over-broad activation increases the chance of misrouting user intent, unexpected behavior, and accidental invocation over other more appropriate skills.
No suspicious patterns detected.
