Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only workflow helper with no code execution or hidden access, though its activation wording is overly broad.
This skill appears safe to install as a workflow/documentation helper. Be aware that it may activate on broad terms like browser, automation, or CLI; explicitly choose it only for agent-browser workflow help, and review any generated automation steps before running them.
The trigger sentence begins with a very broad everyday phrase ('Help me'), which can cause the skill to activate for many unrelated requests. In an agent environment, over-broad routing increases the chance that this skill is invoked in the wrong context, leading to confused delegation, unsafe browser automation guidance, or accidental handling of tasks outside its intended scope.
The trigger sentences are broad, repetitive, and partially generic, making it easier for unrelated user requests containing common workflow terms to invoke this skill unintentionally. In an automation/browser-assistance context, accidental activation can route users into the wrong workflow, causing unsafe guidance, misuse of browser automation patterns, or reduced operator oversight.
The trigger phrases are broad enough to activate the skill for generic terms like 'browser', 'automation', or 'cli', which can cause unintended invocation in contexts unrelated to this skill’s intended use. In an agent ecosystem, ambiguous routing can expose users to incorrect workflows, unsafe automation suggestions, or privilege overreach if the skill is selected for tasks it was not meant to handle.
The manifest description says to use the skill for broad categories such as work-productivity, browser, headless, automation, and practical workflow support, which are common across many unrelated tasks. This ambiguity can lead to unintended invocation, misrouting of requests, and over-application of the skill in contexts where a more specialized or safer skill should respond.
The trigger keywords are extremely generic terms like "browser," "automation," and "cli," which can match many unrelated user requests and cause the skill to activate outside its intended scope. Over-broad invocation increases the chance that users receive irrelevant workflow guidance or that this skill supersedes more appropriate, narrower skills, reducing reliability and potentially affecting safety-sensitive task routing.
The file is specifically authored as SKILL.zh-CN.md, indicating a Simplified Chinese locale variant, but the content does not state that language choice is optional or limited for a justified regional reason. Under the policy, forcing a specific language or locale without user opt-in can be a natural-language policy violation.
The manifest description says to use the skill for broad categories such as work-productivity, browser, headless, and automation, without clear boundaries or exclusion criteria. In a skill-selection pipeline this ambiguity can cause over-selection, misrouting, and inappropriate application of the skill to requests outside its intended scope.
The trigger keywords are very broad and include common terms like browser, automation, cli, and bug fix, which can match many unrelated user requests. This increases the chance of unintended skill invocation, causing the agent to apply irrelevant workflow guidance or override more appropriate skills in mixed-routing environments.
The default prompt is extremely broad and generic, combining many loosely related domains such as work-productivity, browser automation, headless workflows, checklists, analysis, and implementation support without clear scope boundaries. In systems that support prompt-based routing or invocation, this can cause the skill to activate in unintended contexts, increasing the chance of over-collection of user context, misrouting, or unsafe browser-automation assistance being surfaced when not explicitly requested.
Enabling implicit invocation without tightly defined activation boundaries makes the skill eligible to run based on weak or ambiguous matches. Because this skill covers browser-style workflows and automation-related help, unintended invocation could expose users to actions or guidance they did not mean to request, and could allow the skill to influence interactions beyond its intended scope.
The trigger sentence is ambiguous and truncated, so it does not clearly identify when this skill should be used. Ambiguous activation text can cause misrouting and unintended invocation, which is especially relevant here because the skill covers browser/headless automation workflows that may touch sensitive actions or systems.
This file is labeled as a Chinese README, but key descriptive and trigger text remains in English, effectively imposing mixed-language behavior without stating whether users may choose their preferred language. That can conflict with language/locale policy expectations when no opt-in or justification is provided.
The example trigger sentences are truncated and malformed, so they do not provide dependable activation guidance for users or orchestrators. Poor examples can cause inconsistent invocation behavior, confusion about intended scope, and accidental triggering based on vague or partial phrases.
The example trigger phrases use generic language such as 'Help me' and 'I need a practical workflow,' which can collide with ordinary user prompts. Although examples are not executable by themselves, they can train or bias routing systems and maintainers toward overly permissive matching behavior.
No suspicious patterns detected.
