Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only skill for improving error messages, with broad activation wording but no hidden code, persistence, credential use, or destructive behavior.
This appears reasonable to install as a prompt/documentation skill. Users who want tight skill routing should consider narrowing or disabling implicit invocation because broad debugging, support, and productivity wording may cause the skill to be selected more often than intended.
The skill description includes broad invocation terms such as work-productivity, debugging, user feedback, and support that overlap heavily with ordinary user requests. In systems that auto-select skills from natural language, this can cause the skill to activate unexpectedly, intercepting unrelated conversations and creating prompt-routing confusion or unintended instruction precedence.
The trigger keywords and example phrases are highly generic and match common conversational language, especially terms like debugging, support, troubleshooting, and user feedback. This increases the chance of accidental or overly broad skill invocation, which can lead to incorrect routing, hidden prompt injection surface expansion, and unpredictable behavior when the skill is applied outside its intended scope.
The trigger sentence is so broad and awkwardly templated that it can match ordinary user requests about help, workflows, or error messages, causing the skill to activate outside its intended scope. Over-broad invocation criteria can route unrelated conversations into this skill, leading to prompt hijacking of task selection, degraded reliability, and unexpected handling of user data or requests.
The invocation guidance lacks constraints that define when the skill is appropriate versus when a more general assistant behavior should handle the request. This ambiguity can lead to excessive triggering, misrouting, and the application of this skill's workflow to unrelated conversations, reducing reliability and potentially interfering with safer or more suitable handling.
The trigger phrase is extremely broad and maps to common, everyday support and productivity requests, which can cause the skill to activate outside its intended context. Overbroad activation increases the chance of prompt-routing errors, inappropriate skill selection, and unintended influence over unrelated user tasks.
The trigger phrases are extremely broad and match common support or productivity requests, which can cause the skill to activate in many unintended contexts. Overbroad activation increases the chance of prompt hijacking, routing mistakes, or accidental handling of requests outside the skill's intended scope, especially in agentic systems where invocation changes behavior automatically.
The trigger keywords are very broad and map to common support and productivity conversations, which can cause the skill to activate in many ordinary contexts where the user did not explicitly request it. Over-broad activation increases the chance of unintended prompt injection surface, misrouting, or the model prioritizing this skill over more appropriate handling, especially because the skill is framed as generally applicable workflow assistance.
The example trigger phrases begin with generic everyday language like 'Help me' and 'I need', which are common in normal conversation and do not impose meaningful activation constraints. This makes accidental invocation more likely and can let the skill capture unrelated requests, increasing the risk of unintended behavior or prompt-scope confusion in a multi-skill environment.
The default prompt is broad and underspecified, which can cause the skill to be invoked in situations outside its intended scope or with insufficient user intent. While this is not directly a code-execution issue, it can lead to unintended activation, irrelevant assistance, or prompt-routing abuse if other components rely on the description as a trigger.
The evidence list includes Chinese-language content and labels, but the document does not explain whether the skill is intended to operate multilingualy or within a specific locale. This can create a language/locale policy concern because users are not given an explicit language choice or documented scope for how multilingual inputs are handled.
This file is a Chinese-language README variant, but core descriptive and trigger content is presented in English, which can effectively force a language choice on users of the localized document. There is no explicit opt-in or note explaining the language behavior.
