Work Productivity Skillscan Security Workflow Helper

• Outcome: Pass
• Latest audit: Jul 24, 2026 · 5:08 PM UTC
• Version: 0.1.0

Overview

This is a documentation-only workflow helper with overly broad activation wording but no evidence of hidden execution, data access, persistence, or destructive behavior.

Before installing, be aware that this skill may be invoked too easily because its trigger language is generic. It is otherwise a plain workflow/checklist helper; consider narrowing its trigger keywords or disabling implicit invocation if you want tighter routing control.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (13)

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The trigger examples are broad, generic help-seeking phrases that can cause the skill to activate in unrelated contexts. In an agent ecosystem, this creates unintended routing and increases the chance that security-sensitive or unrelated tasks are handled by the wrong skill, which can degrade safety controls and user trust.

Vague Triggers

High

• Confidence: 94% confidence
• Finding: The trigger phrases are broad natural-language requests that overlap with ordinary user prompts, making accidental activation likely. In an agent skill system, this can cause the wrong workflow to run on unrelated requests, which may alter outputs, bypass user intent boundaries, or unexpectedly invoke security-oriented behavior.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The keyword list includes very generic terms like 'security', 'every', 'must', 'pass', and 'before', which are common in normal conversations. This ambiguity increases unintended activation and prompt-collision risk, especially in multi-skill environments where routing decisions may be made automatically.

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The skill description is broad enough to match common words like 'security' and generic requests for workflows, checklists, or analysis, which can cause unintended activation outside the author’s intended domain. In an agent-routing context, this can misroute sensitive or unrelated tasks to this skill, increasing the chance of incorrect automation, policy bypass through skill confusion, or unsafe handling of security-related requests.

Vague Triggers

High

• Confidence: 98% confidence
• Finding: The trigger keywords include highly generic everyday terms such as 'every', 'must', 'pass', and 'before', which are likely to appear in many unrelated prompts. This creates a strong risk of accidental invocation and skill hijacking in multi-skill environments, where routing based on broad keywords can override more appropriate tools or expose the skill to contexts it was not designed to handle.

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: The example triggers are malformed, overly broad, and do not define clear activation boundaries, which reinforces ambiguous routing behavior rather than constraining it. Because examples often serve as activation guidance for maintainers or automated matchers, vague examples can propagate incorrect invocation patterns and increase unintended use in adjacent contexts.

Vague Triggers

High

• Confidence: 97% confidence
• Finding: 触发关键词包含 `security`、`every`、`must`、`pass`、`before` 等高频通用词，边界过宽，容易在与本技能无关的对话中被误触发。误触发后，代理可能引入不相关的流程、检查清单或安全门控步骤，造成行为偏移、上下文污染和潜在的错误自动化决策。

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: 技能描述把适用范围写得较宽，既覆盖 work-productivity，又覆盖 skillscan、安全、gate、artifact、analysis、implementation support 等多个方向，但没有明确排除条件。这样的边界不清会提高路由歧义，使系统在相邻但不适配的请求上调用该技能，降低结果可靠性并可能干扰其他更合适的技能。

Vague Triggers

Medium

• Confidence: 85% confidence
• Finding: 触发示例只展示了会触发的正面案例，没有展示类似措辞但不应触发的负面案例，无法帮助调用方校准边界。在依赖示例进行路由或提示工程的系统中，这会放大误匹配风险，尤其是本技能同时使用了较泛化的主题词时。

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: The default prompt and description are broad enough to match ordinary user requests for general workflow, checklist, analysis, or implementation help. This can cause the skill to activate outside its intended scope, leading to unintended prompt/context injection into unrelated conversations and reducing user control over when the skill is used.

Vague Triggers

High

• Confidence: 95% confidence
• Finding: Enabling implicit invocation without clear activation boundaries allows the system to automatically invoke this skill based on vague, overlapping language. In combination with the broad descriptions above, this increases the likelihood of accidental or excessive invocation, which can expose users to unintended behavior, expanded prompt influence, and confusion about which logic is acting on their request.

Vague Triggers

High

• Confidence: 96% confidence
• Finding: The trigger sentence is extremely broad and can match ordinary user language unrelated to this specific skill, causing unintended activation. Overbroad activation in a security-oriented workflow helper is dangerous because it can hijack routing, insert irrelevant security guidance, or suppress more appropriate skills during normal conversations.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: This trigger pattern uses a generic request form ('I need a practical workflow for...') without a distinct activation boundary, making accidental invocation likely. In an agent ecosystem, ambiguous routing logic can lead to incorrect skill selection, policy bypass by misclassification, or user confusion about why a security-related helper activated.

VirusTotal

64/64 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.