Security audit
Security checks for vulnerabilities and agentic risk
The skill is mostly a non-executable workflow helper, but it can be invoked implicitly using very broad trigger words that may capture unrelated user requests.
Install only if you are comfortable with this skill being auto-selected for broad search, workflow, or bug-fix language. Prefer explicit invocation or narrowed triggers before publishing broadly.
The trigger phrases are broad and generic enough to match ordinary user requests about work, search, integration, or bug fixing, which can cause unintended skill activation. In an agent ecosystem, overbroad routing can hijack unrelated conversations, bypass user intent boundaries, and increase the chance that this skill runs in contexts where it was not explicitly requested.
The description says to use the skill when a user asks for very broad concepts like "work-productivity", "multi", "search", or "engine", which makes activation criteria ambiguous and overinclusive. In an agent environment, broad routing language can unintentionally capture unrelated requests and steer them through this skill, reducing predictability and potentially bypassing more appropriate specialized handling.
The trigger keywords include extremely generic terms like "multi", "search", "engine", and "bug fix", which are likely to appear in many unrelated user requests. This can cause the skill to activate outside its intended scope, creating prompt-routing confusion and increasing the chance that an irrelevant or less-safe workflow is applied to unrelated tasks.
The trigger list includes extremely generic terms such as "multi", "search", "engine", and "global", which are common in ordinary conversations and likely to cause unintended activation. In an agent environment, over-broad triggering can route unrelated user requests into this skill, creating prompt hijacking risk, mis-execution, and reduced reliability because the skill may act on contexts it was not meant to handle.
The default prompt contains broad natural-language triggers such as 'work-productivity', 'workflow', 'checklist', 'analysis', and 'implementation support', which are common across many unrelated user requests. This can cause the skill to activate in contexts the user did not explicitly intend, injecting its prompt and behavior into conversations unexpectedly and increasing the chance of prompt-scope confusion or inappropriate tool use.
Enabling implicit invocation without tight activation constraints allows the platform to invoke this skill automatically based on vague semantic matches rather than clear user intent. Combined with the broad prompt wording, this raises the risk of unintended invocation, prompt injection into benign conversations, and execution of skill-specific behaviors in situations where the user did not request them.
The trigger sentence is extremely broad and includes generic phrasing such as "Help me" combined with a long requirement description, which can cause the skill to activate for ordinary user requests outside its intended scope. Overbroad triggers create prompt-routing risk: the wrong skill may be invoked and steer user interactions toward unrelated workflows, reducing predictability and potentially bypassing more appropriate safety or domain-specific handling.
The trigger phrases are extremely generic and include common terms like 'multi', 'search', 'engine', and broad help-request wording, which can cause the skill to activate outside the intended context. In an agent ecosystem, unintended invocation can route user tasks to the wrong workflow, producing irrelevant actions, bypassing more appropriate skills, or increasing the chance of unsafe automation in contexts the skill was not designed to handle.
The file is a Chinese README, but the listed trigger phrases are only in English and are presented as the usage mechanism without offering a language choice. This effectively forces English-language invocation for a Chinese-localized skill, which is a natural-language policy issue unless the user is given an explicit locale option or justification.
The trigger section provides only broad keywords and positive examples, but no boundary conditions or negative examples to limit use. Without explicit constraints, downstream systems or maintainers may invoke the skill too aggressively, increasing misrouting risk and making behavior less auditable.
The description says to use the skill when users ask for broad categories like work-productivity or search-engine related help, but it does not define clear boundaries for when the skill should or should not activate. This ambiguity increases accidental invocation and tool-selection errors, which can expose users to irrelevant instructions or cause the agent to override a more appropriate, safer workflow.
The invocation description is ambiguous because it does not clearly define when this skill should be chosen instead of other productivity, search, or general workflow skills. Ambiguous routing criteria increase the chance of accidental invocation, which can lead to incorrect task handling, user confusion, and unintended exposure of the skill's instructions in contexts where they do not fit.
