Work Productivity Skillscan Security Workflow Helper

• Outcome: Review
• Latest audit: Jul 24, 2026 · 6:23 PM UTC
• Version: 0.1.0

Overview

This is a documentation-only workflow helper, but its very broad implicit activation settings could make it run during unrelated user requests.

Review this before installing if you rely on precise skill routing. The package appears non-executable and purpose-aligned as a workflow helper, but its activation terms should be narrowed or implicit invocation disabled to avoid the skill appearing in unrelated security, workflow, or bug-fix conversations.

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

High

• Confidence: 94% confidence
• Finding: The trigger sentences are extremely broad and include generic terms and natural-language fragments that could match many unrelated user requests. This can cause unintended skill activation, routing sensitive or ordinary tasks through this skill unexpectedly, which is especially risky for a security-focused workflow helper that may influence analysis or gating decisions.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The keyword list contains highly generic words such as "security," "every," "must," "pass," and "before," which create ambiguous activation conditions and substantial overlap with normal conversation. In a skill system, this raises the chance of accidental invocation, priority hijacking, or misrouting of user intent to this skill.

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The trigger phrases are extremely broad and map to common requests like 'help me' or 'I need a practical workflow', which can cause the skill to activate for many unrelated conversations. In an agent ecosystem, overbroad activation is dangerous because it can unexpectedly insert this skill's workflow into security-sensitive or ordinary tasks, reducing user control and creating prompt-routing confusion.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The keyword list includes generic terms such as 'security', 'every', 'must', 'pass', and 'before', which are likely to appear in many normal requests. This increases accidental activation risk, causing unintended skill selection and possibly interfering with safer or more appropriate routing logic.

Vague Triggers

High

• Confidence: 97% confidence
• Finding: The skill description uses broad activation language such as generic productivity and security-related terms, making it likely to trigger on many unrelated user requests. Over-broad routing can cause the wrong skill to activate, injecting irrelevant instructions into security-sensitive workflows and degrading trust, correctness, and policy compliance.

Vague Triggers

High

• Confidence: 99% confidence
• Finding: The keyword list includes ambiguous single words like 'security', 'gate', 'every', 'must', and 'before', which are common in ordinary conversation and unrelated tasks. This greatly increases accidental activation risk, allowing the skill to hijack routing for broad classes of requests and interfere with more appropriate skills or normal assistant behavior.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The example trigger sentences are malformed and vague, so they do not clearly teach a router or maintainer when activation is appropriate. Poor trigger examples reinforce overmatching and inconsistent behavior, which can cause unintended invocation in adjacent contexts and reduce the reliability of security-related assistance.

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The trigger keywords include very common terms such as "security", "every", "must", "pass", and "before", which can cause the skill to activate in many unrelated conversations. In an agent environment, over-broad auto-activation can inject irrelevant workflow instructions into security-sensitive tasks, creating routing confusion and increasing the chance of inappropriate tool or skill use.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The description says the skill should be used when users ask about broad topics like work-productivity, skillscan, security, or need general workflow or analysis support, but it does not clearly define what requests are out of scope. This ambiguity increases the likelihood of accidental activation and context bleed, especially because some listed topics are broad and overlap with many unrelated tasks.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The example trigger phrases are written like ordinary help requests and do not require a distinct command structure or constrained context. This teaches the router or downstream users that natural-language requests resembling everyday assistance are enough to invoke the skill, which raises the probability of unintended activation.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The default prompt contains a very broad activation phrase tied to generic help-seeking language, which increases the chance of unintended or implicit invocation during unrelated user requests. Because implicit invocation is enabled, this can cause the skill to activate outside its intended scope, potentially injecting workflow guidance or security-related behavior into conversations without clear user intent.

Vague Triggers

High

• Confidence: 96% confidence
• Finding: The trigger guidance includes broad everyday terms like "security," "gate," and especially "every," which can cause the skill to activate for many unrelated user requests. In an agent ecosystem, overbroad activation can route sensitive or unintended conversations into this skill, creating prompt-routing confusion, policy bypass opportunities, or accidental execution of the wrong workflow.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The invocation section mixes generic request phrasing (for example, "Help me" and "I need a practical workflow") with long descriptive requirement text, reducing specificity and making accidental matches more likely. This is dangerous because agents may invoke the skill based on common language rather than user intent, leading to misfires, degraded safety gating, and possible interference with other more appropriate skills.

VirusTotal

64/64 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.