Security audit
Security checks for vulnerabilities and agentic risk
This skill is a local documentation workflow for improving unit test coverage, with broad routing language but no hidden execution, persistence, credential use, or exfiltration behavior.
Before installing, be aware that this skill may activate on broad testing or quality requests. It is otherwise a straightforward unit-test coverage helper, so review whether its trigger wording is precise enough for your environment.
The trigger phrase is so generic that normal user requests about testing or practical workflows could activate this skill unintentionally. Over-broad activation can cause incorrect routing, prompt hijacking of unrelated tasks, and unnecessary exposure of the skill’s instructions or behaviors in contexts where it was not intended to run.
The trigger phrases are generic and map closely to ordinary user requests about testing, coverage, and workflows, which can cause the skill to activate in situations broader than intended. Overly broad invocation increases the chance of misrouting requests, causing the agent to apply this skill in contexts where its assumptions or workflow are a poor fit, which can degrade safety and reliability.
The trigger phrases are generic and highly reusable across many normal software requests, which can cause the skill to activate when the user did not explicitly intend to invoke it. In an agent environment, overly broad activation increases the chance of incorrect tool/skill selection, prompt hijacking through keyword stuffing, or unintended processing paths that bypass more appropriate safeguards.
The skill description and use conditions are broad enough to match many ordinary software or testing requests, which can cause unintended invocation. Over-broad routing is dangerous because it may inject irrelevant instructions or context into unrelated tasks, reducing reliability and potentially overriding more appropriate specialized skills.
The keyword list includes vague terms like 'software-and-data', 'testing', and 'quality', which are too generic for precise activation. This increases the chance of accidental invocation across a large set of unrelated requests, creating prompt-routing errors and unnecessary exposure of skill instructions in contexts where they do not belong.
The activation condition is broadly phrased as applying whenever the user mentions certain software topics or needs related support, without defining clear limits or exclusions. This makes the skill prone to over-triggering on loosely related requests, which can degrade agent behavior and create unsafe prompt-composition or misrouting scenarios.
The trigger keywords include very broad everyday terms like "testing" and "quality", which can cause the skill to activate in contexts far outside unit test coverage work. Over-broad activation increases the chance of prompt routing errors, causing irrelevant or inappropriate guidance to be injected into unrelated tasks.
The default prompt is broad and overlaps with common user requests about software, testing, coverage, and implementation help, which increases the chance of unintended implicit invocation. Because implicit invocation is enabled, normal help-seeking language could trigger this skill without clear user intent, causing prompt routing confusion or unanticipated access to the skill's behavior.
The example trigger sentences use highly reusable, generic phrasing and do not demonstrate clear boundaries for when the skill should be selected. While lower severity than the broad description or keyword list, they reinforce imprecise routing behavior and can bias systems or users toward invoking the skill outside its intended scope.
