Security audit
Security checks for vulnerabilities and agentic risk
The skill is mostly a documentation-only workflow helper, but its activation rules are broad enough that it may be invoked for unrelated security, GitHub, or bug-fix work.
Review the activation scope before installing. The skill does not appear to contain executable or destructive behavior, but its implicit invocation and generic keywords could cause it to steer unrelated security, GitHub, or bug-fix conversations. Prefer narrowing triggers to explicit Skill Vetter or pre-install review requests.
The manifest description includes very broad activation terms such as "security," "first," and generic requests for workflows, checklists, analysis, or implementation support. This can cause the skill to activate for many unrelated prompts, leading to misrouting, unintended invocation, and potentially the application of this skill in contexts it was not designed to handle.
The trigger list contains ambiguous keywords like "security," "first," "before," "github," and "bug fix" without qualifiers or negative examples. In a routing or auto-selection system, these terms are common across many unrelated tasks, increasing the chance of accidental activation and incorrect skill selection, which is especially risky for a skill positioned around vetting and security guidance.
The trigger keywords include very broad terms such as 'security', 'first', 'before', 'github', and 'bug fix', which can match many unrelated user requests. This creates an overbroad auto-activation surface where the skill may be invoked outside its intended scope, causing unintended handling of general security or development tasks and increasing the chance of unsafe or misleading workflow guidance being applied in the wrong context.
The default prompt is phrased broadly enough that common words like "help" and generic workflow/security-related requests could trigger this skill implicitly without clear user intent. Because implicit invocation is enabled, this creates prompt-routing risk where the skill may activate in unrelated contexts, exposing users to unintended behavior or over-broad handling of sensitive productivity or security tasks.
The trigger phrases are extremely broad and include common terms like 'security', 'github', 'before', and generic help-style sentences, which can cause the skill to activate for many unrelated user requests. Over-broad routing increases the chance that this skill intercepts conversations outside its intended scope, leading to incorrect handling, user confusion, and possible bypass of more appropriate or safer skills.
The trigger phrases are very broad, generic, and include common terms like 'security', 'github', and 'bug fix', which can cause the skill to activate outside its intended scope. In an agent ecosystem, over-broad activation can misroute user requests, override more appropriate skills, or cause unintended handling of sensitive security-related tasks.
The trigger phrases are broad and generic enough that the skill may activate in contexts far beyond explicit user intent, including general security, GitHub, or bug-fix requests. In an agent ecosystem, overbroad activation can cause the wrong workflow to run, introduce unintended access to sensitive context, or bias the assistant toward this skill when a narrower or safer tool should be used.
该文件为 SKILL.zh-CN.md，内容整体固定为简体中文区域版本，但未见向用户提供语言选择、回退机制或地区适用性说明。按照该规则，强制特定语言/locale 而无用户选择可能构成自然语言政策问题。
The description says the skill should be used when users mention broad categories like work-productivity, security, or need practical workflows, checklists, analysis, or implementation support. Because these categories are vague and boundary-less, the skill can be selected for many requests beyond 'Skill Vetter-style workflows,' leading to scope confusion and possible misuse of templated security guidance in contexts it was not designed to handle.
The README lists separate English and Chinese instruction files, but it does not explain whether the user's language preference is respected or how the appropriate locale is selected. This can create an implicit language/locale behavior without documented user opt-in.
Although this is a Chinese README, substantial instructional content and trigger phrases are presented in English without explaining language-selection behavior or offering user opt-in. This can create an implicit language/locale constraint or mismatch for users expecting a fully Chinese-localized skill description.
