Work Productivity Skillscan Security Workflow Helper

• Outcome: Pass
• Latest audit: Jul 24, 2026 · 6:53 PM UTC
• Version: 0.1.0

Overview

This is a documentation-only workflow helper with no executable behavior, but its auto-activation wording is broader than it needs to be.

Before installing, be aware that this skill may be selected for broad security or workflow-related prompts. It is safest to invoke it explicitly or narrow the trigger terms to SkillScan-specific phrases. I found no evidence that it reads files, uses credentials, installs packages, runs commands, persists in the background, or sends data elsewhere.

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 (9)

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The trigger keywords and example phrases are broad enough to match many unrelated requests, which can cause this skill to activate outside its intended scope. In a security-oriented workflow helper, over-broad activation increases the chance of inappropriate invocation, user confusion, and accidental routing of sensitive or irrelevant tasks into a security gate process.

Vague Triggers

High

• Confidence: 94% confidence
• Finding: The trigger phrases are extremely broad and include generic security and workflow terms such as 'security', 'gate', 'every', 'must', and 'before', which can cause the skill to activate in many unrelated contexts. In an agent ecosystem, overbroad activation can route sensitive or security-relevant tasks through the wrong skill, creating prompt-routing confusion, unsafe handling of requests, or unintended interference with other controls.

Vague Triggers

High

• Confidence: 98% confidence
• Finding: The skill description and activation guidance are broad enough to match many unrelated user requests, increasing the chance of unintended auto-activation. In an agent environment, accidental invocation can inject irrelevant instructions or workflow behavior into otherwise normal conversations, reducing reliability and potentially bypassing user intent boundaries.

Vague Triggers

High

• Confidence: 99% confidence
• Finding: The keyword list includes highly generic words such as 'security', 'gate', 'every', 'must', 'pass', 'before', 'activate', and 'bug fix', which are common across many unrelated prompts. Such vague triggers can cause excessive matching and unauthorized or inappropriate skill activation, making the agent's behavior unpredictable and easier to steer off task.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The example trigger sentences use generic lead-ins like 'Help me' and 'I need', which fail to define a meaningful activation boundary and reinforce overbroad matching behavior. This makes it more likely that ordinary assistance requests will be interpreted as requests for this skill, causing confusion and incorrect workflow injection.

Vague Triggers

High

• Confidence: 96% confidence
• Finding: The trigger list includes very generic words such as "security", "gate", "every", "must", "pass", "before", and "activate", which are likely to appear in many unrelated user requests. This can cause unintended activation of the skill, leading to prompt-routing errors, overbroad invocation, and possible interference with other safer or more appropriate skills in security-sensitive workflows.

Natural-Language Policy Violations

Medium

• Confidence: 81% confidence
• Finding: The skill metadata and body mix Chinese with embedded English terms and trigger phrases without any locale-selection or language-preference guidance. This can cause ambiguous matching, user confusion, and misactivation across language contexts, especially when routing depends on keywords rather than explicit user intent.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The skill enables implicit invocation while exposing a very broad description and default prompt, allowing the platform to auto-select it for loosely related requests such as 'workflow', 'analysis', or 'security'. This increases the chance of unintended activation, prompt-surface expansion, and execution in contexts the user did not clearly authorize, which can lead to confused-deputy behavior or unsafe handling of sensitive tasks.

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The trigger sentences and keywords include very broad, everyday terms such as "security," "gate," "every," and "bug fix," which can cause the skill to activate for unrelated requests. In an agent environment, unintended invocation can misroute tasks, override more appropriate skills, and increase the chance that sensitive or security-relevant workflows are handled by the wrong automation path.

VirusTotal

64/64 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.