Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only workflow skill with overly broad auto-invocation cues but no evidence of hidden code, credential access, persistence, or data exfiltration.
Before installing, consider narrowing or disabling implicit invocation so ordinary writing, editing, review, or bug-fix requests do not unexpectedly use this skill. The inspected package is advisory documentation only, so the main practical risk is misrouting rather than compromise.
The trigger phrase examples are extremely broad and resemble normal user requests, which can cause the skill to activate outside its intended scope. In an agent environment, over-broad activation can route unrelated tasks through this skill, leading to prompt hijacking of workflow selection, confusion, or misuse of downstream actions.
The description says to use the skill when a user asks for broad categories such as work-productivity, practical workflow, artifact, checklist, analysis, or implementation support, which are common across many benign requests. This ambiguous activation condition can cause frequent false-positive routing and make the agent apply this skill in situations far outside its intended scope.
The trigger keywords are broad, generic terms like "writing," "text," "editing," and "reviewing," which can cause this skill to activate during ordinary user requests unrelated to the intended workflow. Over-broad activation increases the chance of unintended skill execution, misrouting, and unsafe application of specialized guidance in contexts where it was not requested.
The trigger sentence is broad and resembles normal user language, which can cause the skill to activate when a user did not explicitly intend to invoke it. In an agent environment, unintended invocation can route unrelated user requests through this skill, causing prompt hijacking of task flow, incorrect outputs, or bypass of more appropriate skills.
The trigger examples are generic enough to match ordinary user requests about help, workflows, bug fixes, or hardening, which can cause the skill to activate outside its intended scope. Over-broad invocation increases the chance of accidental routing, unexpected behavior, and misuse of a skill in contexts where it was not explicitly requested.
This Chinese README includes substantive English instruction text instead of consistently using the user's apparent locale. That can amount to a language-policy issue because the file presents content in a fixed language mix without indicating user choice or opt-in.
The invocation guidance does not define when this skill should versus should not be used, which increases accidental or adversarial triggering. Without boundary conditions and counterexamples, common phrasing can overlap with unrelated tasks and cause incorrect skill routing in multi-skill agent systems.
The example trigger sentences use highly generic phrasing such as "Help me" and "I need a practical workflow," which closely resembles normal user speech. If examples are used by routing or matching systems, this can increase accidental invocation and reduce reliability by colliding with unrelated conversations.
The activation description says to use the skill when users mention broad terms like work-productivity, humanizer, remove, signs, or generated, or whenever they need practical workflow or implementation support. Because these conditions are vague and expansive, the skill may be selected for many unrelated requests, increasing the risk of misapplication and unexpected behavior in an agent system.
The trigger list includes very generic terms such as "writing", "text", "editing", "reviewing", and "bug fix", which overlap with many ordinary user requests unrelated to this skill’s stated purpose. This can cause the skill to activate in unintended contexts, leading to incorrect routing, over-broad delegation, or accidental application of workflows to unrelated tasks.
The default prompt is phrased in broad, everyday language and includes generic terms like 'help me' and broad work-productivity concepts, which can cause the skill to be selected in situations far outside its intended scope. This increases the risk of accidental or inappropriate invocation, expanding the attack surface for prompt injection, unintended task routing, or user confusion.
Enabling implicit invocation without tight scope restrictions allows the system to auto-select this skill based on loosely related user phrasing. In combination with the broad skill description, this can cause the agent to invoke the skill unexpectedly, leading to overreach, incorrect handling of user requests, or abuse through crafted prompts that intentionally trigger the skill.
This trigger uses a generic request form ('I need a practical workflow for...') without requiring clear scope or explicit invocation, making accidental matching likely. Such ambiguous activation increases the chance that the skill intercepts user requests outside its intended domain and influences system behavior in unexpected ways.
The usage section presents trigger sentences only in English, while the evidence section includes Chinese-language sources, yet the document does not state whether the skill supports multiple languages or requires English input. This can amount to an implicit language preference without user opt-in or documented locale handling.
