Security audit

Work Productivity Weather Current Workflow Helper

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only workflow helper with overly broad activation language, but it does not request sensitive access, persistence, or automatic system actions.

Install only if you want a lightweight workflow-planning helper for weather/current API style skill work. Be aware it may activate too often because its trigger terms are broad; prefer explicit invocation and consider narrowing the trigger language before publishing widely.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (12)

Vague Triggers

High

Confidence: 90% confidence
Finding: The trigger phrases are broad, generic, and partially malformed, which increases the chance that the skill will activate for unrelated everyday requests involving weather, work, APIs, or bug fixes. Overbroad activation can cause unintended routing, prompt injection exposure through irrelevant contexts, and user confusion about why this skill was invoked.

Vague Triggers

Medium

Confidence: 86% confidence
Finding: The invocation guidance does not define clear scope boundaries, so the agent may select this skill for a wide range of common requests unrelated to the intended workflow-helper function. In an agent ecosystem, ambiguous routing increases the attack surface by causing unnecessary exposure of skill instructions and enabling incorrect tool use in contexts the skill was not designed to handle.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The trigger phrases are broad and include generic terms like "weather", "api", and "bug fix", which can cause the skill to activate in contexts the user did not intend. In an agent ecosystem, unintended invocation can route user requests into the wrong workflow, producing inappropriate actions, irrelevant outputs, or unsafe tool usage if downstream steps assume the skill was deliberately selected.

Vague Triggers

High

Confidence: 95% confidence
Finding: The manifest description is extremely broad and matches common user intents such as 'workflow,' 'analysis,' 'implementation support,' and generic weather/API terms. This can cause the skill to activate in contexts far outside its intended scope, increasing the chance of prompt-shadowing, misrouting, or unintended handling of unrelated tasks.

Vague Triggers

High

Confidence: 98% confidence
Finding: The trigger keyword list includes very common words like 'current,' 'api,' 'key,' 'required,' 'users,' and 'bug fix,' which are likely to appear in many benign conversations. Overbroad triggers can lead to unintended invocation and priority hijacking, where this skill intercepts requests meant for other skills or generic assistant behavior.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The example trigger sentences teach activation patterns built around generic phrases like 'Help me' and 'I need,' which are ubiquitous in normal user requests. This increases the likelihood that routing systems or maintainers will preserve unsafe activation behavior, causing accidental invocation in unrelated contexts.

Vague Triggers

High

Confidence: 95% confidence
Finding: 触发关键词包含非常通用的词，如“weather”“current”“api”“key”“users”“required”，会让该技能在大量无关对话中被误触发。误触发会把用户请求错误路由到本技能，造成上下文污染、错误建议，且在涉及密钥或 API 的对话中会放大安全与隐私暴露风险。

Vague Triggers

Medium

Confidence: 86% confidence
Finding: 技能描述把触发条件表述为一组宽泛主题词加“或需要实用流程/分析/实现支持”，边界非常模糊，几乎可覆盖大量普通生产力或 API 求助场景。这样的启用条件会导致技能选择器过度匹配，使本技能在不适合的上下文中介入，降低系统可靠性并可能干扰更合适的安全控制或专用技能。

Vague Triggers

Medium

Confidence: 90% confidence
Finding: 示例触发句使用“Help me”“I need a practical workflow for”这类高度通用的开头，容易与日常求助语句重叠，从而训练或暗示路由器在缺乏明确领域信号时也触发本技能。其危险性低于直接的宽关键词列表，但会进一步增加误触发概率并削弱技能边界。

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The default prompt includes broad, common-language trigger terms such as "help me" and a wide set of generic concepts, which can cause the skill to be invoked in contexts unrelated to its intended purpose. Because implicit invocation is enabled, this increases the chance of unintended routing, prompt hijacking opportunities, or accidental use of this skill on unrelated user requests.

Vague Triggers

High

Confidence: 95% confidence
Finding: The trigger sentence is extremely broad and written like a common help request, which can cause the skill to activate in contexts the user did not intend. In an agent ecosystem, overbroad invocation increases the chance of accidental routing, context hijacking, or the skill handling unrelated tasks with misleading authority.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The invocation guidance is ambiguous because it mixes generic productivity language with weather, APIs, bug fixing, and adjacent-skill creation, without defining a precise activation boundary. This makes accidental invocation more likely and can let unrelated prompts be captured by the skill, reducing predictability and potentially exposing sensitive task context to an unintended workflow.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.