Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only workflow helper with overly broad triggers but no evidence of hidden execution, credential access, persistence, or data exfiltration.
Before installing, be aware that this skill may activate on broad Google Workspace or bug-fix wording even when you did not specifically intend to use it. It appears safe as a documentation/workflow helper, but users should prefer explicit invocation when working around Gmail, Calendar, Drive, or other sensitive productivity contexts.
The skill description and usage guidance are broad enough to match many ordinary productivity or Google-related requests, which can cause unintended invocation. Overbroad activation increases the chance the wrong skill handles user tasks, leading to incorrect actions, scope creep, or accidental processing of sensitive workspace data under the wrong workflow assumptions.
The trigger keywords include highly generic terms such as 'google', 'workspace', 'cli', and 'bug fix', which are likely to collide with many unrelated requests. This makes accidental invocation likely and can route users into an inappropriate workflow, reducing reliability and potentially exposing unrelated tasks or sensitive context to a mis-scoped skill.
The trigger list includes very common terms such as "google", "workspace", "cli", and "bug fix", which can cause the skill to activate for many unrelated requests. Over-broad invocation increases the chance that this skill intercepts prompts outside its intended scope, leading to user confusion, incorrect routing, or unintended application of workflow guidance.
The trigger sentences and keywords are broad enough to match many ordinary productivity or Google Workspace requests, which can cause the wrong skill to auto-activate outside its intended scope. In an agent ecosystem, this creates routing confusion and may lead users to receive irrelevant workflow guidance, increasing the chance of mistaken actions or unsafe assumptions in adjacent tasks.
The trigger guidance lacks precise boundaries and mixes generic keywords ('google', 'workspace', 'bug fix') with vague natural-language trigger examples, making the activation surface overly broad. In a productivity skill that may influence workflows around communication and files, this can cause unintended invocation, task hijacking, or confusion about when the skill should control the interaction.
The trigger sentence is written as a natural-language help request rather than a narrowly scoped invocation, which increases the chance that ordinary user conversation could unintentionally activate the skill. In an agent ecosystem, accidental activation can route tasks into the wrong workflow, causing unintended actions, misleading outputs, or over-broad access to connected productivity contexts like Gmail, Calendar, or Drive.
The trigger phrases are broad and include common terms like "google," "workspace," "cli," and generic requests for "practical workflow," which can cause the skill to activate for routine user requests far outside its intended scope. In an agent ecosystem, over-broad routing can lead to inappropriate tool selection, unexpected handling of sensitive productivity data, or unsafe execution paths because the skill is invoked in contexts it was not designed to handle.
The file is primarily in Chinese while the metadata and broader ecosystem may be multilingual, and it does not state that the user has opted into Chinese output. This can cause the skill to respond in an unexpected language, which may lead to misunderstanding of instructions, missed safety caveats, or incorrect execution of workflow steps.
The description says to use the skill for broad categories like work-productivity, gog, google, workspace, or whenever a user needs a practical workflow, checklist, analysis, or implementation support. This activation scope is vague enough that the orchestrator may invoke the skill in many loosely related contexts, reducing predictability and increasing the risk of mismatched assistance.
The default prompt is overly broad and generic, making it easier for the skill to be invoked in situations that only loosely relate to the intended use case. Because implicit invocation is enabled, this increases the chance of unintentional routing, which can cause the agent to apply the wrong workflow, expose unrelated context to the skill, or override a more appropriate tool.
This file is named as a Chinese-language README, but substantial user-facing content including the title, demand description, workflow description, and trigger phrases is presented in English. That can amount to an implicit language policy inconsistency because the skill does not offer a user language choice or explain why English-only phrasing is required in this locale-specific document.
