Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only workflow helper with overly broad activation signals, but it does not contain code execution, credential access, persistence, or hidden data movement.
Install this only if you want a broad workflow-planning helper. Because implicit invocation is enabled and the trigger words are generic, users or maintainers should prefer explicit invocation or tighten triggers to avoid the skill being selected for unrelated tasks.
The trigger phrases are broad enough to match many ordinary user requests, which can cause this skill to activate outside its intended scope. In an agentic workflow context, over-triggering is dangerous because it can steer unrelated tasks into this skill’s workflow, increasing the chance of unintended actions, prompt hijacking, or workflow substitution without clear user intent.
The description says to use the skill when a user asks for broad concepts like work-productivity, proactive, transform, task, or any practical workflow/artifact/checklist/analysis support. That invocation condition is so expansive that it can capture a large fraction of ordinary requests, increasing the chance of accidental activation and inappropriate handling of user tasks.
The trigger list is excessively broad and includes generic terms like "task," "transform," "needs," and "bug fix," which are common in ordinary user requests. This can cause the skill to activate in unintended contexts, leading to prompt hijacking of unrelated workflows, user confusion, or routing sensitive requests into an ill-fitting agent behavior.
The trigger list includes very broad, everyday terms such as "task", "needs", and "bug fix", which can cause the skill to activate in many unrelated conversations. Over-broad activation increases the chance of unintended routing, prompt-context pollution, and the skill being invoked in situations where its assumptions or workflow are inappropriate.
Enabling implicit invocation without tight trigger constraints allows the platform to activate this skill opportunistically based on weak keyword or intent matches. In combination with the broad productivity-oriented description, this can cause unauthorized or unexpected engagement of the skill, increasing the risk of prompt-scope creep, unintended actions, or interference with other workflows.
The trigger sentence is broad and generic enough that ordinary user requests about help, workflows, tasks, or productivity could accidentally invoke this skill outside its intended scope. In an agent ecosystem, unintended invocation can cause the wrong workflow to run, leading to irrelevant automation, confusion, or downstream actions being taken under incorrect assumptions.
The trigger keywords include very broad, everyday terms such as "task," "transform," and "needs," which can cause the skill to activate in unrelated conversations. In an agentic environment, overbroad activation increases the chance of unintended workflow injection, context hijacking, or accidental execution of the wrong skill when the user did not explicitly request it.
The example trigger sentences are vague and partially formed, using broad phrasing like "Help me" and "I need a practical workflow" without strong disambiguation. This makes accidental activation more likely and can let ordinary user requests be misrouted into this skill, which is especially risky for an agent intended to proactively transform or structure tasks.
The file is a Chinese README but substantial operational content, including the skill title, core description, and trigger phrases, is presented in English. This can amount to an implicit language constraint or inconsistent locale behavior without user opt-in or an explicit language-selection mechanism.
The description says to use the skill for broad categories like work-productivity, proactive, transform, or task, but does not clearly define exclusion criteria or precise invocation conditions. This ambiguity can lead to accidental activation and misapplication of the skill, especially in multi-skill environments where several skills may match similar user requests.
The default prompt is overly broad and ambiguous, encouraging invocation for a wide range of loosely related requests rather than a narrowly scoped task. This increases the chance the agent is invoked in contexts the user did not clearly intend, which can lead to confusing behavior, overreach, or unsafe application of the skill's capabilities.
The trigger guidance is ambiguous because it mixes very broad keywords with incomplete example sentences and does not define boundaries for when the skill should or should not activate. This increases the chance of over-triggering, especially in shared agent environments where routing decisions may rely heavily on these usage signals.
