Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only workflow helper with broad activation wording but no hidden code, persistence, credential use, or destructive behavior.
Install only if you want a general Agent Browser workflow helper. Be aware that its trigger terms are broad, so users or maintainers may want to narrow activation wording to avoid accidental use for ordinary browser, CLI, automation, or bug-fix requests.
The manifest description contains very broad activation terms like 'browser', 'automation', and generic help phrasing, which can cause the skill to match many unrelated user requests. This increases the chance of unintended invocation, causing the agent to apply the wrong workflow or expose users to unexpected behavior in contexts where a more specific skill should handle the task.
The triggers list uses broad keywords such as 'browser', 'automation', 'cli', and 'bug fix' without boundaries or negative examples, making accidental activation likely. In an agent environment, overbroad triggers can hijack routine requests and route them through an irrelevant skill, reducing reliability and potentially interfering with safer or more appropriate task handling.
The trigger sentences are extremely broad, repetitive, and partially truncated, which can cause the skill to activate for loosely related requests rather than clear user intent. In an automation/browser-workflow context, over-triggering is risky because it may steer users into powerful workflow guidance or browser-oriented actions when they did not explicitly ask for that capability.
The trigger phrases are broad, repetitive, and partially generic terms such as "browser", "automation", and "practical workflow", which increases the chance the skill is invoked outside the author's intended context. In an agent environment, unintended invocation can route user requests into the wrong workflow, causing misleading automation guidance, unnecessary actions, or expansion of the skill's operational scope.
The skill description defines activation conditions using a wide set of generic categories, including work-productivity, browser, headless, and automation, without clear boundaries. This makes the skill eligible for many loosely related requests, which is dangerous because agent systems may apply its guidance in inappropriate contexts and amplify mistakes or unsafe assumptions.
The trigger list includes very broad everyday terms such as "browser", "automation", and "cli", which can cause the skill to activate in many unrelated contexts. In an agent environment, over-broad triggering can route user requests to the wrong skill, increasing the chance of unintended instruction application, confusion, or unsafe workflow suggestions outside the intended scope.
The default prompt is framed as a broad natural-language trigger ('Use $work-productivity-agent-browser-workflow-helper to help me ...') tied to common concepts like work productivity, browser, and automation, while the policy also allows implicit invocation. That combination can cause the skill to be invoked in contexts broader than intended, increasing the chance of untrusted content influence, accidental delegation, or unexpected workflow execution in a browser-automation setting.
The invocation section does not clearly define activation scope, exclusions, or required conditions, so the skill may be invoked for loosely related browser, automation, or productivity requests. In an agent environment, ambiguous routing increases the chance of misapplication, causing the wrong workflow, assumptions, or automation guidance to be used without clear user intent.
The trigger sentence uses a very broad, natural-language phrase ('Help me ...') tied to a long requirement description rather than a narrowly scoped invocation pattern. This can cause accidental or unintended activation when ordinary user requests partially match the phrase, leading the agent to apply this skill in contexts where it was not explicitly requested.
A file presented as Chinese-language documentation includes substantial English content for the title, demand description, workflow description, and trigger phrases. This can create a language-policy issue because the skill appears to impose English phrasing in a locale-specific document without user opt-in or explanation.
