Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only workflow helper with broad activation wording but no hidden execution, credential access, persistence, or destructive behavior.
Review the broad trigger terms before installing if you rely on automatic skill routing; otherwise this skill appears safe for producing productivity workflows and checklists, with no evidence of hidden code execution or account access.
The skill description and activation guidance are broad enough to match common requests involving "google," "workspace," "cli," or generic workflow help, which increases the chance of unintended invocation. Overbroad routing can expose users to the wrong skill behavior, create prompt-scope confusion, and make it easier for unrelated tasks to be steered into this skill without clear user intent.
The keyword list contains highly generic everyday terms such as "google," "workspace," "cli," "gmail," "calendar," and "drive," which are likely to collide with many unrelated user requests. In an agent ecosystem, this can cause frequent accidental invocation, misrouting of user intent, and increased attack surface for prompt interference via deliberate trigger stuffing.
The description says the skill should be used whenever a user asks for broad categories like work-productivity, google, workspace, cli, or any practical workflow, checklist, analysis, or implementation support for the requirement. This is so expansive that it blurs the boundary of the skill's scope, making unintended invocation and misrouting substantially more likely.
The trigger list includes very common terms such as "google", "workspace", "cli", "gmail", and "calendar", which can cause the skill to activate in many unrelated contexts. Over-broad invocation increases the chance that users are routed into this skill unintentionally, leading to irrelevant guidance, context confusion, or accidental handling of tasks the skill was not specifically intended for.
The trigger phrases are excessively broad and include common help-seeking language such as 'Help me' and 'I need a practical workflow,' which can cause the skill to activate for many unrelated requests. In an agent ecosystem, this can lead to unintended routing, over-privileged handling of user tasks, and confusion about which skill should respond, especially because the skill also claims broad keywords spanning work-productivity, Google Workspace, CLI, and bug fixing.
The trigger sentences are broad, natural-language phrases that resemble ordinary user requests rather than narrowly scoped invocation patterns. This can cause accidental skill activation in unrelated conversations, leading the agent to apply this workflow when the user did not explicitly intend to invoke it, which is especially risky because the skill is positioned around Google Workspace and workflow assistance.
The trigger examples are generic enough to match ordinary productivity or workflow requests, which can cause the skill to activate outside its intended scope. In an agent ecosystem, this increases the chance of unintended invocation, over-broad access to Google Workspace-related contexts, and user confusion about why this skill was selected.
The example trigger sentences rely on generic wording like "help me" and "I need a practical workflow," without clarifying what uniquely identifies this skill. Ambiguous examples train routing systems and authors toward loose activation patterns, increasing unintended selection and making malicious or irrelevant prompt shaping easier.
The file is a zh-CN skill document, but the core description embeds substantial English text and examples without stating whether the user can choose their preferred language. This may impose a language/locale behavior without clear opt-in or documented justification.
The default prompt uses very broad language such as helping with general workflow, productivity, analysis, implementation, and common tool categories, which overlaps with many ordinary user requests. Combined with implicit invocation, this broad activation surface can cause the skill to be invoked in contexts where it was not specifically intended, creating routing abuse and unsafe overreach risks.
The skill enables implicit invocation with no visible trigger constraints, exclusions, or narrowing conditions. That makes it easier for the agent platform to auto-select this skill for loosely related requests, increasing the chance of prompt-scope hijacking, unintended execution, or interference with user intent.
