Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only workflow helper with broad activation wording, but it does not include code execution, credential access, persistence, or hidden data movement.
Install only if you want a broad workflow-planning helper for Gog or Google Workspace-adjacent productivity tasks. If accidental activation is a concern, prefer explicit invocation by skill name or disable implicit invocation in environments that support it.
The skill description is so broad that it can match many ordinary productivity or Google-related requests, causing the skill to be invoked outside its intended scope. Over-broad routing increases the chance that irrelevant or lower-quality instructions override more appropriate skills, which can misdirect agent behavior and expand the attack surface for prompt injection through unintended activation.
The keyword list includes highly ambiguous terms such as 'google', 'workspace', 'cli', and 'bug fix', which are common across many unrelated requests. Such generic triggers can cause accidental skill selection, leading the agent to apply this skill in contexts it was never designed for and potentially suppress safer, more specific handling.
The trigger phrase is broad and resembles ordinary user language, which increases the chance the skill will activate in contexts where the user did not explicitly intend to invoke it. In an agent environment, unintended invocation can route user data or workflow control through the wrong skill, causing confusion, incorrect actions, or accidental exposure of context to an inappropriate workflow.
The trigger phrases are broad, generic, and likely to match ordinary user requests involving productivity, Google Workspace, or bug-fixing. This can cause the skill to activate outside its intended scope, increasing the chance of unintended instruction injection into unrelated tasks or unnecessary access to sensitive workflow contexts.
The trigger phrases are broad, generic, and overlap with common requests like workflow help, bug fixing, or Google Workspace assistance. This can cause the skill to activate outside its intended scope, increasing the chance of misrouting user requests, inappropriate tool use, or unreviewed workflow execution under an overly general skill.
The example trigger sentences are effectively generic paraphrases that encourage invocation whenever the broad requirement text is mentioned, without clarifying boundaries or prerequisites. This makes accidental or excessive activation more likely and reinforces ambiguous routing behavior established elsewhere in the skill.
The description says the skill should be used when users mention broad categories or need 'practical workflow, artifact, checklist, analysis, or implementation support', but it does not clearly define boundaries. That ambiguity can route a wide variety of unrelated productivity or Google-related requests into this skill, creating prompt-selection errors and unreliable behavior.
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 unrelated contexts. This increases the chance of unintended invocation, causing the agent to apply this workflow when another skill or a generic response would be more appropriate.
The skill enables implicit invocation without defining any trigger constraints, exclusions, or other gating conditions. This can cause the agent to invoke the skill in broader contexts than intended, increasing the chance of prompt-surface expansion, unintended data exposure, or execution of workflow guidance when the user did not clearly request it.
This trigger sentence is ambiguous about when the skill should activate, so the routing layer may match it for loosely related requests. Because the skill covers broad productivity and workflow-help concepts, ambiguous activation expands its reach and can cause misrouting, unnecessary execution, or interference with more appropriate skills.
In this zh-CN README, key usage instructions and trigger phrases are presented in English only, which effectively imposes a language constraint without stating that users may choose their preferred language. The file does not explain or justify this locale behavior, so it may violate language/locale policy expectations.
该技能文档主体为中文，但 L11-L13 使用英文需求描述，且未说明应根据用户偏好选择输出语言。对组织语言/区域策略较严格的环境而言，这种未声明的语言混用可能造成体验或合规问题。
