Security audit

Work Productivity Skill Vetter Workflow Helper

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only workflow helper with no executable code, but its automatic invocation terms are overly broad and may trigger unintentionally.

Install only if you want a general skill-vetting workflow helper. Be aware that its broad implicit triggers could cause it to activate during unrelated security, GitHub, or bug-fix requests; narrowing the trigger keywords or requiring explicit invocation would make it cleaner.

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 (10)

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The trigger phrases are broad enough to activate on generic terms like 'security', 'github', or 'bug fix', which can cause the skill to run in contexts the user did not explicitly intend. In an agent environment, overbroad activation increases the chance of inappropriate workflow invocation, misrouting user requests, or overshadowing more suitable skills, especially for security-sensitive tasks.

Vague Triggers

High

Confidence: 92% confidence
Finding: The trigger phrases are broad, generic, and include common terms such as 'security', 'first', 'github', and 'bug fix', which can cause the skill to activate in contexts far beyond its intended scope. In an agent ecosystem, this creates skill-confusion and routing risk: users may invoke this workflow unintentionally, leading to inappropriate handling of requests or interference with more suitable skills.

Vague Triggers

High

Confidence: 94% confidence
Finding: The skill description and use guidance are broad enough to match many ordinary requests, including generic 'security' or 'first' phrasing unrelated to this specific workflow. Overbroad activation can cause incorrect skill selection, leading the agent to apply the wrong instructions or expose users to unintended workflow behavior in security-sensitive contexts.

Vague Triggers

High

Confidence: 97% confidence
Finding: The keyword list includes highly ambiguous generic terms such as 'security', 'first', 'before', 'github', and 'bug fix', which are likely to collide with many unrelated user prompts. In an agentic system, this can hijack routing and invoke this skill in contexts it was not designed for, increasing the chance of misleading guidance or interference with more appropriate security workflows.

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The example trigger sentences are vague, truncated, and centered on broad natural-language activation rather than clear invocation boundaries. This reinforces permissive matching behavior and makes accidental or opportunistic triggering more likely, especially because the examples do not distinguish this skill from general productivity or security help.

Vague Triggers

High

Confidence: 94% confidence
Finding: 触发关键词包含非常宽泛的常用词，如“security”“first”“before”“github”“bug fix”，会让技能在大量无关对话中被误触发。对一个涉及“vetter/security”工作流的技能来说，误触发会扩大其影响面，导致模型在不合适的上下文中套用该技能流程、覆盖更相关技能，或把安全分析带入普通任务中。

Vague Triggers

Medium

Confidence: 88% confidence
Finding: 技能描述中的启用条件覆盖范围过大：既包含宽泛主题词，也包含“需要实用流程、产物、检查清单、分析或实现支持”这类几乎可适用于许多任务的表述。这样的边界不清会导致技能被频繁错误选中，使其在非预期场景中处理请求，增加提示词干扰、错误工作流应用和权限/决策混淆的风险。

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The skill enables implicit invocation but defines no narrow trigger constraints, so it may activate on loosely related requests without clear user intent. Because this is a security/vetting helper, unexpected activation could cause the agent to introduce security-analysis behavior, workflow changes, or sensitive-context processing in situations where the user did not explicitly request this skill.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The default prompt uses broad, generic wording such as 'help me' and references common tasks like fixing bugs, hardening setup, improving reliability, and creating workflows. This overlap with ordinary user requests increases the chance of unintended routing or prompt injection into unrelated conversations, especially when combined with implicit invocation.

Vague Triggers

High

Confidence: 97% confidence
Finding: The trigger sentences are broad enough to match generic requests about security, vetting, GitHub, or bug fixes, which can cause the skill to activate outside its intended scope. In an agent ecosystem, unintended invocation is dangerous because it can route user tasks to the wrong workflow, create misleading authority for security-sensitive guidance, and increase the chance of prompt-surface abuse through accidental triggering.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.