Work Productivity Skillscan Security Workflow Helper

• Outcome: Review
• Latest audit: Jul 29, 2026 · 7:07 AM UTC
• Version: 0.20260729.110214

Overview

This is a documentation-only workflow helper, but it should be reviewed because it can be implicitly invoked for very broad security and productivity wording beyond its stated purpose.

Review this skill before installing if your environment auto-selects skills. It does not appear to run code or access data by itself, but its trigger wording should be narrowed or implicit invocation disabled so ordinary security or productivity requests are not routed through it unexpectedly.

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 (14)

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The trigger sentences are broad, natural-language phrases that can match common user requests unrelated to this specific skill. In an agent ecosystem, this can cause unintended auto-activation, leading the skill to intercept or influence workflows outside its intended scope and potentially override more appropriate skills or controls.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The keyword list contains highly generic terms like 'security', 'gate', 'every', 'must', 'pass', 'before', and 'activate', which are likely to appear in many unrelated requests. This creates ambiguous activation scope and increases the chance that the skill is selected inappropriately, which is especially risky for a workflow helper that may shape security decisions or operational actions.

Vague Triggers

High

• Confidence: 96% confidence
• Finding: The trigger phrases are broad natural-language requests that can match many ordinary user prompts unrelated to this skill’s intended scope. In an agent ecosystem, this can cause unintended auto-activation, routing sensitive or unrelated tasks through the skill and increasing the chance of misuse, prompt hijacking, or incorrect security gating behavior.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The keyword set includes generic terms such as 'security', 'every', 'must', 'pass', and 'bug fix', which are common across many unrelated requests. This ambiguity weakens activation boundaries and can make the skill trigger in contexts where users did not intend it, creating unsafe delegation and noisy security workflow invocation.

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The trigger keywords are extremely broad and include common words like "security," "every," "must," "pass," and "before," which can cause accidental activation during unrelated conversations. In an agent environment, this can lead to inappropriate skill routing, prompt-context contamination, or execution of the wrong workflow when users did not intend to invoke this skill.

Vague Triggers

High

• Confidence: 90% confidence
• Finding: The description says to use the skill when a user asks for very broad concepts like "work-productivity," "security," or any practical workflow or checklist support, without defining scope limits. Such ambiguous activation conditions increase the chance that the skill is selected for unrelated requests, which can misroute user intent and expose unnecessary instructions or context to the agent pipeline.

Vague Triggers

Medium

• Confidence: 86% confidence
• Finding: The example trigger phrases are malformed, incomplete, and not representative of realistic user requests, so they do not provide reliable guidance for safe invocation. Poor examples make it harder to distinguish intended activation from incidental text matches, increasing accidental routing and inconsistent agent behavior.

Vague Triggers

High

• Confidence: 97% confidence
• Finding: The trigger keyword list includes extremely common terms such as "security", "every", "must", "pass", and "before", which can cause the skill to activate in many unrelated conversations. Over-broad activation increases the chance that this skill will be invoked outside its intended scope, potentially overriding more appropriate skills or injecting workflow guidance into unrelated tasks.

Vague Triggers

High

• Confidence: 94% confidence
• Finding: The manifest description says to use the skill when a user asks for broad categories like work-productivity, security, gate, or any practical workflow/checklist/analysis support for the requirement. This is so expansive that routing systems or operators may invoke the skill in contexts far beyond the intended job-to-be-done, creating prompt-scope confusion and increasing the risk of unintended behavior.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The example trigger phrases are generic request templates such as "Help me..." and "I need a practical workflow...", which do little to constrain when the skill should fire. In systems that learn or pattern-match from examples, these broad exemplars can further widen activation and cause false-positive routing into this skill.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The default prompt is overly broad and uses generic everyday phrasing such as 'help me' and broad topic terms, which increases the chance of unintended routing or activation for loosely related user requests. In a skill focused on security workflows, this can cause the agent to invoke the skill outside its intended scope and expose users to irrelevant or risky guidance paths.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: Enabling implicit invocation without clear activation boundaries allows the platform to auto-select this skill based on vague semantic matches rather than deliberate user choice. Because the skill is framed around security and workflow assistance, accidental invocation could misroute sensitive requests, create confusing behavior, or bypass expected user intent checks.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The trigger sentence is broad enough to match ordinary user phrasing rather than a clearly bounded invocation, which can cause unintended activation of this skill. In an agent environment, accidental routing to a security/gating helper can alter workflow selection, produce irrelevant outputs, or interfere with higher-priority skills when common words are used as triggers.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: This trigger uses a generic request pattern ('I need a practical workflow for...') without clear boundaries, making it likely to match many unrelated prompts. Such ambiguity increases the chance of misrouting and prompt-surface expansion, especially because the skill metadata already includes broad terms like 'security', 'gate', and 'every' that can overlap with normal conversation.

VirusTotal

64/64 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.