Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only workflow helper with overly broad activation text, but no hidden execution, credentials, persistence, or destructive behavior.
Install only if you want a general workflow helper for Gog-style Google Workspace productivity tasks. Be aware it may activate on broad terms like google, workspace, cli, gmail, calendar, or drive, so users should confirm the skill is relevant before following its workflow advice.
The skill description is broad enough to match common terms like 'google', 'workspace', 'cli', and generic requests for workflows or analysis, which can cause unintended invocation. Over-broad routing can expose users to the wrong skill behavior, reduce reliability, and create opportunities for prompt-surface expansion where an irrelevant skill influences sensitive tasks.
The keyword list includes highly generic terms such as 'google', 'workspace', 'cli', 'gmail', 'calendar', and 'drive', which are common across many unrelated tasks. This makes accidental activation likely and can misroute broad categories of user requests into this skill, increasing the chance of incorrect guidance or unintended access to adjacent capabilities.
The trigger list includes very broad, high-frequency terms such as "google", "workspace", and "cli", which are likely to match many unrelated user requests. This can cause accidental skill activation, leading the agent to apply the wrong workflow or inject irrelevant instructions into unrelated tasks, reducing reliability and potentially affecting security-sensitive decisions.
The trigger sentence begins with a very broad everyday phrase ('Help me ...'), which can match many unrelated user requests and cause unintended skill activation. In an agent ecosystem, over-broad routing increases the chance that this skill is invoked outside its intended scope, leading to confusing behavior, prompt-surface expansion, and possible misuse of any downstream actions tied to the skill.
The trigger sentence starts with the overly broad phrase 'Help me', which can match many ordinary user requests unrelated to this skill. In an agent ecosystem, ambiguous activation can cause unintended routing or invocation, increasing the chance the skill handles requests outside its intended scope and leading to incorrect actions or user confusion.
The phrase 'I need a practical workflow' is highly generic and does not uniquely identify this skill's purpose. Because the skill targets broad work-productivity and Google-related tasks, this ambiguity makes accidental activation more likely and may cause the agent to apply this workflow in unsuitable contexts.
The trigger phrases are broad and match generic productivity/help requests, which can cause the skill to activate in situations far beyond its intended scope. In an agent ecosystem, this increases the chance of incorrect routing, unintended invocation, and unsafe application of workflow guidance to unrelated tasks involving Gmail, Drive, Calendar, or general CLI/workspace operations.
The example trigger phrases use ordinary language like 'help me' and 'I need a practical workflow' without establishing clear boundaries for activation. This trains integrators toward permissive matching behavior and reinforces over-triggering, which can make the skill activate in contexts far outside its intended scope.
The invocation description says to use the skill for broad categories like work-productivity, gog, google, workspace, and cli, without defining clear boundaries for when it should or should not activate. This ambiguity increases the chance of misrouting general productivity or Google-related requests into this skill, creating unsafe overreach and inconsistent behavior.
The default prompt embeds a broad, natural-language invocation phrase that can match common user requests like help with work productivity, workflows, or implementation support, without strong scoping constraints. Combined with allow_implicit_invocation=true, this increases the chance the skill is auto-invoked in contexts the user did not clearly intend, which can cause unintended tool routing, prompt-surface expansion, or misuse of the skill in unrelated conversations.
This trigger remains ambiguous because it describes a broad need for a 'practical workflow' without sufficiently constraining the domain, inputs, or expected task boundaries. That ambiguity can cause accidental invocation for unrelated productivity requests, reducing reliability and potentially exposing users to irrelevant or unintended workflow behavior.
