Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-style workflow helper with broad activation wording, but it does not include executable code, credential access, persistence, or hidden data movement.
Install only if you want a broad productivity workflow helper and are comfortable with it being eligible for implicit invocation. Review or narrow the trigger keywords if your environment routes skills automatically for Google Workspace, CLI, Gmail, Drive, Calendar, Contacts, or bug-fix requests.
The skill description and activation guidance are broad enough to match many ordinary requests involving 'google', 'workspace', 'cli', or generic workflow help. This can cause the wrong skill to activate and steer users into irrelevant or unintended instructions, increasing the chance of confused-deputy behavior or accidental handling of tasks outside the skill's intended scope.
The keyword list includes highly ambiguous, high-collision terms such as 'google', 'workspace', 'cli', and 'bug fix' with no contextual constraints. In an automated routing environment, these generic triggers can hijack a large volume of unrelated requests, causing inappropriate tool or skill selection and potentially exposing users to incorrect actions in sensitive productivity contexts.
The trigger keywords are overly broad and include common terms like 'google', 'workspace', 'cli', and 'bug fix', which can cause the skill to activate for many unrelated user requests. This increases the chance of accidental routing or shadowing of other skills, leading to confused delegation, irrelevant outputs, and potentially unsafe handling if the wrong workflow is applied to a user task.
The trigger sentence starts with a very broad, everyday phrase ('Help me ...'), which is likely to match many unrelated user requests and cause unintended invocation. In an agent ecosystem, over-broad routing can expose users to irrelevant automation, increase prompt-surface for downstream actions, and make it easier for a skill to activate outside its intended scope.
The trigger sentences are generic and semantically broad enough that unrelated user requests about Google Workspace, workflows, bug fixes, or productivity could invoke this skill unintentionally. In an agent ecosystem, over-broad activation can route sensitive tasks to the wrong skill, causing unintended actions, privacy exposure, or unsafe automation without clear user intent.
The trigger phrases are broad, generic, and overlap with common terms like 'google', 'workspace', 'cli', and 'bug fix', which can cause the skill to activate for many unrelated user requests. In an agent environment, this increases the chance of unintended routing or invocation, potentially leading to the wrong workflow handling sensitive productivity tasks or user data.
The example trigger sentences are vague and repetitive, and they do not establish clear boundaries for when the skill should activate versus when it should not. Poor examples increase misrouting risk by teaching downstream systems or authors to invoke the skill for broad, underspecified requests rather than precise, validated use cases.
The description embeds substantial English text inside an otherwise Chinese skill file, and the trigger examples also rely on English phrasing. This can implicitly force a language preference without documenting user choice or opt-in.
The example trigger phrases are written as generic everyday requests like 'Help me...' and 'I need a practical workflow...', without clear markers that distinguish skill invocation from normal conversation. This makes accidental activation more likely and can cause the orchestrator to select this skill for broad productivity requests that were not meant for it.
The default prompt uses broad language like 'help me,' which overlaps heavily with normal user conversation and creates ambiguous matching behavior. Combined with a general-purpose productivity theme, this makes accidental invocation more likely and can cause the agent to apply this skill in unrelated contexts.
The skill enables implicit invocation without any constrained trigger conditions, so it may activate during ordinary conversations that loosely match the domain. This increases the risk of unintended tool routing, prompt-scope confusion, and overbroad exposure of the skill in contexts where the user did not explicitly request it.
Although this trigger adds some context, it is still ambiguous because it describes a broad class of 'practical workflow' needs rather than a precise, bounded use case. That can still cause accidental matches and misrouting, especially since the skill metadata also spans many general terms like work-productivity, google, workspace, and cli.
The file states that the skill instructions and user-facing guides exist in English and Chinese, but it does not say that the user can choose their preferred language or that language handling is opt-in. Because locale/language policy findings apply to all file types, this can be read as an undocumented language constraint.
The file labels this document as the Chinese user guide and references separate English and Chinese documentation files, but it does not indicate any user choice or opt-in for language selection within the skill description. Under the policy, locale-specific behavior should either offer a language choice or clearly justify the constraint.
