Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only skill for improving error messages, with some overly broad activation wording but no evidence of hidden execution, data access, persistence, or destructive behavior.
Installers should expect a lightweight writing and workflow aid for clearer error messages. The main thing to watch is activation scope: because implicit invocation is enabled and keywords are broad, it may be selected for general debugging or support requests unless the platform or user narrows usage to error-message improvement tasks.
The trigger sentence is so broad and unnatural that it can match ordinary user requests about help, workflows, or error handling rather than an intentional invocation of this specific skill. That creates a routing/invocation ambiguity where the skill may activate in contexts the user did not explicitly request, causing unintended prompt injection surface expansion and incorrect task handling.
The trigger sentences are broad and generic enough that the skill may activate in many ordinary support, debugging, or productivity contexts without clear scoping. Over-broad activation can cause unintended routing to this skill, increasing prompt-injection exposure and allowing the skill to influence tasks outside its intended bounds, though the README itself does not contain directly malicious behavior.
The trigger phrases are broad enough to match many ordinary support or productivity requests, which can cause the skill to activate outside its intended scope. In an agent system, overbroad activation expands the skill's influence over user workflows and can lead to inappropriate routing, confused delegation, or accidental processing of unrelated user input.
The skill description is very broad and overlaps with common support, debugging, productivity, and implementation tasks. In agent routing systems, this can cause unintended invocation, leading the skill to intercept unrelated requests and shape responses in contexts where it was not specifically intended, which can reduce reliability and create opportunities for prompt-scope confusion.
The trigger keywords and example phrases are generic enough to match a wide range of ordinary support or debugging requests that may have nothing to do with improving error messages. This increases the chance of accidental activation, which can misroute user intent, override more appropriate skills, and expand the skill's effective authority beyond its intended domain.
The description defines a very wide activation scope using generic categories like work-productivity, debugging, support, and user feedback, without precise inclusion or exclusion criteria. In a routing system, this increases the chance of unintended invocation across many everyday requests, which can interfere with correct skill selection and expand the skill's effective authority beyond its intended niche.
The sample trigger phrases are written as broad natural-language requests that overlap with ordinary user intent, making accidental invocation more likely. This can cause the wrong skill to activate in unrelated contexts, leading to misrouting, confusing outputs, or unreviewed handling of user requests.
The default prompt is written in broad, everyday language covering work productivity, debugging, user feedback, support, workflows, artifacts, checklists, analysis, and implementation support. Because this wording overlaps heavily with common user requests, it can cause overbroad matching and accidental invocation, especially when combined with implicit invocation, making the skill more likely to activate outside its intended niche.
The skill enables implicit invocation without any trigger phrases, domain boundaries, or other activation constraints, so it may be selected for a wide range of ordinary support or debugging requests. This increases the chance of unintended routing, where the agent invokes the skill in contexts the author did not specifically scope, potentially exposing user content to an unnecessary tool path or causing behavior the user did not explicitly request.
The file declares separate English and Chinese instruction and guide files, but the README does not state how the user's language preference is selected or that language choice is optional. This can create an implicit locale policy without user opt-in.
This Chinese-language README contains substantial English user-facing description text, which can impose a language choice on users without opt-in. The file does not explain whether bilingual output is intentional or offer a language/locale choice.
No suspicious patterns detected.
