Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only workflow helper with no executable payload, though its broad implicit triggers may cause it to activate for unrelated writing or bug-fix requests.
Install only if you want a generic workflow helper for humanizer-style productivity tasks. Be aware that its implicit triggers are broad, so it may be selected for ordinary writing, editing, reviewing, or bug-fix prompts unless your agent lets you control or disable implicit invocation.
The manifest description says to use the skill when a user asks for broad categories such as work-productivity or practical workflow support, which are common across many benign tasks. This ambiguous 'use when' clause can cause excessive or incorrect invocation, making the skill act outside its intended scope and potentially override more appropriate skills or controls.
The trigger keywords are extremely broad and include common terms like writing, text, editing, reviewing, and bug fix, which can cause this skill to activate for many unrelated requests. Over-broad activation increases the chance the wrong workflow is injected into normal conversations, leading to unintended behavior, prompt-scope interference, and reduced reliability of agent routing.
The skill description and activation guidance are broad enough to match many unrelated user requests, increasing the chance of unintended invocation. In an agent environment, overbroad routing can cause the wrong workflow to run, leading to irrelevant actions, unsafe modifications, or bypass of more appropriate specialized skills.
The keyword list includes very common terms such as writing, text, editing, reviewing, and bug fix, which are too generic to safely control skill activation. These terms are likely to appear in many benign conversations, so the skill may trigger unexpectedly and interfere with routing, causing the agent to apply the wrong instructions or workflow.
The trigger sentence begins with a very broad everyday help request and can match many unrelated user prompts, causing the skill to activate outside its intended scope. In an agent environment, over-broad invocation can route users into unintended workflows, increasing the chance of irrelevant actions, confused delegation, or accidental application of this skill to sensitive tasks.
This trigger pattern is a generic request template ('I need a practical workflow for...') without meaningful scope boundaries, so ordinary productivity requests may accidentally invoke the skill. Because the skill is positioned as broadly applicable workflow support, the lack of constraints makes unintended activation more likely and reduces predictability of agent behavior.
The trigger examples are so broad and generic that they can match ordinary user requests unrelated to this specific skill, increasing the chance of accidental invocation or misrouting. In an agent ecosystem, overbroad routing can cause the wrong workflow to run, producing unintended edits or actions under the guise of a relevant productivity task.
The trigger phrases are broad and partially match common user requests, which can cause the skill to activate when the user did not specifically intend to use it. In an agent ecosystem, unintended invocation can route tasks through the wrong workflow, producing irrelevant actions, confusing outputs, or unsafe automation in contexts the user did not explicitly select.
The example trigger sentences are generic and effectively restate broad help-seeking language rather than demonstrating constrained invocation boundaries. In practice, this trains or encourages invocation on vague requests, increasing false activations and making downstream agent behavior less predictable.
The example trigger phrases model vague invocation patterns and encourage activation from loosely related language instead of requiring a clearly scoped request. This trains users or calling systems to invoke the skill on underspecified prompts, increasing accidental use and misapplication of the workflow.
The default prompt is overly broad and uses generic terms like 'help me' and common workflow language, which can cause the skill to be invoked for ordinary requests outside its intended scope. Because implicit invocation is enabled, this increases the chance of accidental routing, prompt-surface expansion, and unintended influence over unrelated user tasks.
The file descriptions specify separate English and Chinese instruction files, implying language-specific operation, but the README does not state that users can choose their preferred language at runtime. This can create an implicit locale constraint without explicit user opt-in.
