Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only workflow helper whose main risk is overly broad auto-activation, not hidden execution or data access.
Installers should be aware that this skill may be selected for broad Google, Workspace, CLI, or bug-fix requests because implicit invocation is enabled. It appears safe as a planning/checklist helper, but maintainers should narrow triggers to avoid accidental activation.
The trigger sentences are broad enough to match ordinary productivity and workflow requests, which can cause this skill to activate outside its intended scope. In an agent ecosystem, overbroad routing can misdirect user tasks to a skill with access to Google Workspace-related workflows, increasing the chance of unintended actions, confusion, or unsafe delegation.
The trigger phrases are broad enough that ordinary requests containing generic terms like work-productivity, google, workspace, or bug fix could invoke the skill unintentionally. In an agent ecosystem, unintended invocation can route user tasks into the wrong workflow, causing confused execution, inappropriate access attempts to Google-related actions, or accidental use of a skill in contexts the user did not explicitly intend.
The trigger list is overly broad and includes generic terms like "google," "workspace," and "cli," which can cause this skill to activate for many unrelated requests. Over-broad routing increases the chance that users are steered into an irrelevant workflow, causing prompt-selection errors, confusing outputs, or unintended handling of tasks outside the skill's intended scope.
The example trigger phrases are written in very generic natural language and closely resemble ordinary user requests, making accidental invocation more likely. Because the skill presents itself as broadly applicable implementation support, ambiguous examples can override better-matched skills and lead to misrouting or unsafe assumptions about user intent.
The description says to use the skill whenever the user mentions broad topics or needs general 'support', but it does not define clear scope boundaries or disambiguation criteria. This ambiguity can cause accidental invocation on loosely related tasks, increasing the risk of misrouting, inappropriate instructions, or unintended access paths if the surrounding agent system grants skills different capabilities.
The trigger keywords are overly broad and include common terms like 'google', 'workspace', 'cli', and 'bug fix', which can cause the skill to activate in many unrelated conversations. Overbroad activation increases the chance that this skill hijacks routing from more appropriate skills, leading to unintended handling of user requests and weakened security boundaries around tool selection.
The default prompt is phrased broadly enough that ordinary user requests about work productivity, Google Workspace, workflows, checklists, or implementation help could unintentionally trigger this skill. That creates prompt-scope confusion and increases the chance the agent injects this skill into contexts the user did not explicitly request, which can lead to inappropriate actions or unsafe reliance on the skill.
Enabling implicit invocation without defined scope restrictions allows the platform to auto-select this skill based on loose semantic matches rather than explicit user consent. In a broadly described productivity skill, that raises the likelihood of unintended activation, prompt injection into unrelated tasks, and overreach into workflows where the skill is not appropriate.
The activation guidance lacks clear boundaries for when the skill should and should not be invoked, making it easy for orchestration logic to over-match unrelated requests. In a productivity skill that references broad domains like work-productivity, google, workspace, and cli, this ambiguity increases the chance of misrouting user tasks, accidental tool use, and bypass of more appropriate specialized controls.
The trigger sentences are phrased broadly enough that ordinary user requests could accidentally activate this skill outside its intended scope. In an agent system, ambiguous activation can cause the wrong workflow to run, leading to unintended access to Google/Workspace-adjacent tasks, irrelevant automation, or unsafe task routing without clear user intent.
This file is presented as a Chinese README, but key user-facing descriptive content is written in English. That can amount to a language-policy issue because the document implicitly forces English for part of the experience without stating that users may choose a language or that English is required for a specific reason.
