Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-style workflow helper with broad activation wording but no executable code, persistence, credential handling, or hidden behavior.
Installers should be aware that this skill may activate on generic browser or automation requests because its triggers are broad. Review or narrow the trigger phrases if precise skill routing matters; otherwise the artifact is a low-risk workflow/documentation helper.
The skill description and usage criteria are broad enough to match common terms like browser, automation, and work-productivity, which can cause the skill to be invoked for many unrelated requests. Over-triggering can route users into the wrong workflow, leading to unsafe assumptions, irrelevant automation advice, or accidental handling of tasks outside the skill’s validated scope.
The keyword list includes vague, high-frequency terms such as browser, headless, automation, cli, and bug fix without qualifiers, making accidental activation likely. In an agent ecosystem, this broad matching increases the chance of the skill intercepting unrelated tasks and producing overconfident outputs in contexts where its assumptions do not hold.
The trigger phrase is extremely broad ('Help me ...') and can match ordinary user requests that are not specifically about this skill, causing unintended invocation. In an agent ecosystem, over-broad activation can route unrelated tasks into a browser/automation-oriented workflow, increasing the chance of inappropriate actions, confusion, or unsafe downstream automation.
The trigger sentences are broad, repetitive, and match generic requests about browser, automation, or workflow help, which increases the likelihood that the skill will activate outside the author's intended scope. In an agent ecosystem, unintended invocation can cause the wrong workflow or instructions to be applied to user tasks, creating safety, reliability, and least-surprise issues even without explicit malicious content.
The trigger phrases are broad enough to match common user requests about browsers, automation, CLI, or productivity, which can cause this skill to activate in contexts the user did not intend. In an agent ecosystem, overbroad activation can route tasks to a workflow with browser/headless automation semantics unnecessarily, increasing the chance of unintended actions, misleading outputs, or unsafe task expansion.
The skill description defines activation using a wide set of loosely related categories, including work-productivity, browser, headless, and automation, without clear scoping rules. This makes the skill eligible for many generic prompts, increasing the chance of accidental invocation and inappropriate handling of tasks outside its intended domain.
The trigger list includes very broad everyday terms such as "browser", "automation", and "cli", which can cause the skill to activate for many unrelated requests. Over-broad activation can route users into an unintended workflow, producing irrelevant guidance or causing the agent to prioritize this skill over a more appropriate one.
The default prompt uses broad, common terms like work-productivity, browser, automation, checklist, analysis, and implementation support, which creates unclear activation boundaries. This can cause the skill to be invoked in unrelated contexts, increasing the chance of prompt-scope confusion, unintended tool use, or the skill influencing tasks the user did not explicitly intend to delegate to it.
Enabling implicit invocation without tight scope constraints allows the platform to auto-select this skill based on ambiguous user language. In a broadly described browser and productivity domain, that raises the risk of unintended activation, context leakage across tasks, and accidental execution of automation-oriented behavior in situations where the user did not request this skill.
The sentence 'I need a practical workflow for ...' is still generic enough to match many benign productivity requests without clearly requiring this exact skill. Because the skill is positioned around browser-style workflows and automation, ambiguous triggering can over-expand the skill's reach and lead to accidental activation in contexts where safer or more appropriate skills should handle the request.
The file lists English and Chinese instruction and guide files as fixed language variants, but does not state how language is selected or whether the user can choose their preferred locale. This can create a locale-policy concern if the skill defaults to a language without explicit user opt-in.
This file is labeled as a Chinese README, but several user-facing sections and trigger phrases are presented in English only, such as the title, core description, and invocation examples. That can amount to forcing a language/locale on users without explicit opt-in or documented justification.
