Work Productivity Skillscan Security Workflow Helper

• Outcome: Review
• Latest audit: Jul 24, 2026 · 5:21 PM UTC
• Version: 0.1.0

Overview

This documentation-only workflow skill does not show malware behavior, but its automatic activation rules are broad enough to steer unrelated user requests.

Install only if you are comfortable with this skill being auto-selected for broad security or workflow-related wording. A safer version should require explicit invocation or narrower SkillScan-specific trigger phrases.

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 (11)

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The trigger sentences are broad, natural-language phrases that could cause the skill to activate on ordinary user requests unrelated to an explicit invocation. In a security/workflow helper context, overbroad activation increases the chance of unintended routing, causing the agent to apply this skill in situations where a different skill or stricter security review would be more appropriate.

Vague Triggers

Medium

• Confidence: 96% confidence
• Finding: The trigger section includes broad generic words and phrases such as "security", "gate", "every", "must", "pass", "before", and "activate", plus natural-language trigger examples that could match ordinary user requests. This can cause unintended skill activation, leading the agent to invoke the workflow in unrelated contexts and potentially bypass user intent or interfere with safer skill-routing decisions.

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The trigger keywords are extremely broad and include common terms like "security," "every," "must," and "before," which can cause the skill to activate in many unrelated contexts. This increases the chance of incorrect routing, unintended invocation, and prompt-surface expansion where the skill influences tasks it was not designed to handle.

Vague Triggers

High

• Confidence: 92% confidence
• Finding: The description says to use the skill when a user asks for broad categories like work-productivity, skillscan, security, gate, or every, without defining scope limits. In agent systems, this kind of open-ended activation rule can cause over-selection of the skill, mis-handle user intent, and increase exposure to irrelevant or sensitive workflows.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The example trigger sentences model vague natural-language phrasing instead of requiring a specific call pattern, which trains selectors or users toward opportunistic invocation. This makes accidental activation more likely and reinforces the overly broad routing behavior already present elsewhere in the file.

Vague Triggers

High

• Confidence: 96% confidence
• Finding: The trigger keyword list includes overly generic terms such as "security", "gate", "every", "must", "pass", and "before", which are common in unrelated conversations. This can cause the skill to activate in unintended contexts, increasing the chance that it injects workflow guidance where it was not requested and interferes with other skills or normal agent behavior.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The usage condition in the description is broad and underspecified, saying the skill should be used when users mention very general topics or need generic workflow artifacts. Ambiguous scope increases accidental invocation and makes it hard for an agent router to distinguish this skill from many unrelated productivity or security requests.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The example trigger phrases begin with generic formulations like "Help me" and "I need a practical workflow," but do not provide contrasting non-trigger examples. This trains or encourages broad matching behavior, which can increase false activations and reduce routing precision.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The skill enables implicit invocation while providing only a vague, expansive description of when it should be used. This can cause the agent to auto-select the skill for ordinary productivity or security-related requests that only loosely match the description, expanding the skill's influence beyond clearly user-intended boundaries.

Vague Triggers

Medium

• Confidence: 96% confidence
• Finding: The default prompt uses broad everyday phrases such as 'help me' and generic workflow/security language that overlap heavily with common user requests. When combined with skill routing, this increases the chance of unintended activation or prompt injection into unrelated tasks, which can steer responses in ways the user did not explicitly request.

Vague Triggers

High

• Confidence: 96% confidence
• Finding: The trigger phrases are broad, generic, and include common terms such as 'security', 'gate', 'every', and 'bug fix', which are likely to match ordinary user requests unrelated to this specific skill. This can cause accidental invocation or over-selection of the skill, increasing the chance that the agent applies the wrong workflow or exposes users to unintended processing paths.

VirusTotal

VirusTotal findings are pending for this skill version.

Static analysis

No suspicious patterns detected.