Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only workflow helper with overly broad trigger wording but no executable, hidden, persistent, or credential-seeking behavior.
Install this only if you want a general workflow helper for proactive-agent style productivity tasks. Its generic trigger words may make it activate unexpectedly, so prefer explicit invocation or narrow the trigger metadata if your agent platform supports that.
The trigger keywords and example invocations are broad, generic, and partially unrelated to a clearly bounded task, which can cause the skill to activate in contexts the user did not intend. In an agent workflow setting, over-activation can misroute requests, override more appropriate skills, or cause unintended autonomous behavior, increasing the chance of unsafe or confusing outputs.
The manifest description says to use the skill when a user asks for broad concepts like 'work-productivity', 'proactive', 'transform', 'task', or practical support, which are ambiguous and likely to match ordinary requests. This makes invocation logic unreliable and can cause unintended skill selection, especially in systems that auto-route based on descriptions.
The trigger list is extremely broad and includes common terms like 'task', 'needs', and 'proactive', which can cause the skill to activate in many unrelated conversations. Overbroad activation increases the chance of unintended routing, context pollution, and accidental execution of workflows the user did not request.
The trigger list includes very broad everyday terms such as "task", "needs", and "partners", which can cause the skill to activate in unrelated conversations. Over-broad activation increases the chance that the agent injects workflow guidance when not requested, creating unintended prompt routing and reducing user control over which skill is invoked.
The trigger sentence is broad enough to match ordinary user language such as asking for 'help' or a 'practical workflow,' which can cause accidental skill activation outside its intended scope. In an agent environment, over-broad activation can route unrelated tasks through this skill, leading to incorrect behavior, prompt-surface expansion, and possible chaining into workflows the user did not intend.
The trigger phrases are broad, generic, and include common workflow terms such as 'help me', 'practical workflow', 'task', and 'proactive', which increases the chance the skill is invoked in contexts the user did not intend. In an agent ecosystem, unintended invocation can cause the wrong workflow to take over a conversation, produce irrelevant artifacts, or interfere with safer or more specific skills.
This Chinese README presents key usage content, including the workflow description and trigger phrases, in English only. That can amount to a language-policy issue because the file targets zh-CN users but does not offer an explicit language choice or opt-in for English instructions.
The example trigger sentences are truncated and malformed, so they do not provide a dependable invocation pattern for either users or automated routers. Poor examples can lead to misfires, accidental matching on partial phrases, and inconsistent behavior across agent platforms.
The file is entirely in Chinese and does not state language selection behavior or fallback handling. In a multilingual agent environment, this can cause incorrect activation or outputs in a language the user did not request, which harms usability and may cause users to misunderstand operational or safety guidance.
The description says the skill should be used when users ask for broad categories like work-productivity, proactive, transform, or need practical support, but it does not define clear boundaries for when the skill should or should not engage. This ambiguity can lead to over-selection of the skill, causing misrouting, irrelevant assistance, or interference with more appropriate skills.
The manifest uses very broad trigger wording in both the description and default prompt, including generic terms like "work-productivity," "proactive," "task," "workflow," "artifact," and "analysis." Combined with allow_implicit_invocation: true, this increases the chance the skill is auto-invoked for loosely related user requests, causing unintended routing, unexpected behavior, or overexposure of this skill in contexts the user did not explicitly request.
The invocation guidance does not clearly define when the skill should versus should not activate, so adjacent requests may be ambiguously captured. This increases the risk of overreach, where the agent applies this skill to loosely related prompts and produces workflow transformations the user did not request, reducing reliability and potentially exposing more context to unnecessary processing.
