Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only workflow helper with overly broad activation wording but no hidden execution, persistence, credential access, or destructive behavior.
Install only if you want a broad workflow-planning helper for proactive-agent-style productivity tasks. Be aware it may activate on generic productivity wording, so review outputs for relevance when your request was not specifically about this workflow.
The trigger phrases are very broad and include generic terms like 'task', 'needs', 'help me', and 'I need a practical workflow', which can cause the skill to activate for many ordinary requests outside its intended scope. In an agent ecosystem, overbroad invocation increases the chance of unintended routing, context capture, or execution of the wrong workflow, reducing safety and predictability.
The trigger list includes very generic terms such as "task," "transform," "needs," and "partners," which are common in ordinary user requests. This can cause the skill to activate far outside its intended scope, leading to inappropriate routing, prompt interference, or accidental application of this workflow in unrelated contexts.
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 contexts. Over-broad activation increases the chance that this skill overrides more appropriate skills or injects workflow guidance when the user did not intend to invoke it, creating prompt-routing and safety-control issues.
The trigger sentence begins with a highly generic help-request phrase, which can cause the skill to activate for ordinary user prompts that were not intended to invoke this workflow. In an agentic environment, overly broad activation increases the chance of context confusion, accidental tool routing, or execution of an irrelevant workflow based on partial keyword matches.
The trigger phrases are broad and include generic terms like 'help me', 'practical workflow', 'transform', and 'task', which can cause the skill to activate in contexts beyond the user's intent. In an agent setting, ambiguous activation boundaries increase the risk of the skill inappropriately steering conversations or overriding more relevant skills, producing unintended actions or misleading workflow guidance.
This Chinese-language README contains substantial English-only instructional content, which can effectively force a specific language experience without user opt-in. The file does not explain the mixed-language policy or offer an alternative within this document.
The description says to use the skill when a user asks for broad concepts like work-productivity, proactive, transform, task, or practical workflow support, but it does not clearly define boundaries. That ambiguity increases the chance of over-selection and misuse of the skill in contexts where a more specific or safer skill should handle the request.
The example triggers are truncated, repetitive, and do not demonstrate realistic boundaries between matching and non-matching cases. Poor trigger examples make it easier for orchestration systems or maintainers to interpret the skill too broadly, increasing unintended activation and lowering reliability.
The description says to use the skill when a user asks for broad categories like work-productivity, proactive, transform, or task, without defining clear boundaries. This ambiguity can cause unintended invocation across a wide range of normal requests, making routing less predictable and potentially exposing users to irrelevant or unsafe automated assistance.
The default prompt contains very broad activation language tied to common terms like work-productivity, proactive, transform, task, checklist, and analysis. This can cause the skill to be invoked in contexts the user did not specifically intend, increasing the chance of prompt-scope hijacking, unintended tool routing, or accidental disclosure of context to the skill.
Enabling implicit invocation without activation constraints allows the platform to auto-route user requests to this skill based on loose relevance signals rather than explicit consent. In a broadly described productivity skill, this raises the risk of unintended invocation, cross-context prompt injection exposure, and actions or guidance being applied where the user did not request this workflow helper.
This trigger is underspecified and broad enough that many unrelated requests for a 'practical workflow' could match, leading to unintended activation. Because the skill is framed as a general workflow helper, weak activation boundaries make misrouting more likely and can cause the agent to provide inappropriate automation or analysis in the wrong context.
The file explicitly documents only English and Chinese instruction and guide files, which suggests a fixed language set without any stated user opt-in or language selection behavior. Under the language/locale policy, skills should offer a language choice or clearly justify a locale constraint.
