Work Productivity Self Improving Workflow Helper

• Outcome: Pass
• Latest audit: Jul 29, 2026 · 7:43 AM UTC
• Version: 0.20260729.110214

Overview

This is a documentation-style workflow helper with no executable code or credential handling, though its automatic invocation terms are broader than ideal.

Installers should be aware that this skill may activate on broad self-improvement or productivity language. It is best used when explicitly requested by name or for self-improving/proactive agent workflow help; otherwise, accidental invocation could produce irrelevant planning guidance.

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

High

• Confidence: 93% confidence
• Finding: The trigger sentence is so broad that ordinary user requests for generic help could unintentionally invoke this skill, causing it to intercept prompts outside its intended scope. In an agent ecosystem, ambiguous routing can lead to prompt hijacking-by-selection, unexpected behavior, or application of self-improving/proactive workflows where the user did not explicitly request them.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The invocation description uses broad natural-language phrasing without clear trigger boundaries, which increases the chance that common requests will match unintentionally. Because this skill is framed for proactive/self-improving behavior, accidental invocation is more dangerous than for a passive informational skill, since it may alter workflow decisions or produce actions the user did not clearly ask for.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The trigger phrases are broad, generic, and overlap with common words such as 'self', 'improving', and 'proactive', which can cause unintended activation in unrelated contexts. In an agent ecosystem, this increases the chance that the skill runs when not explicitly requested, potentially steering workflows, producing irrelevant actions, or interfering with safer/more appropriate skills.

Vague Triggers

High

• Confidence: 98% confidence
• Finding: The trigger list includes extremely broad terms such as 'self', 'improving', and 'proactive', which are common in ordinary user prompts and unrelated tasks. This can cause unintended activation of the skill, leading the agent to apply the wrong workflow, override more appropriate skills, or expose users to unexpected autonomous-style behavior in contexts where it was not requested.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The invocation description says to use the skill whenever a user asks for broad concepts like work-productivity, self, improving, proactive, or practical workflow support, without clearly limiting the domain. This ambiguity increases the chance of misrouting many unrelated requests into this skill, producing incorrect assistance or causing this skill to preempt more suitable and safer specialized skills.

Vague Triggers

High

• Confidence: 96% confidence
• Finding: The trigger list includes extremely generic terms such as “self”, “improving”, and “proactive”, which are likely to appear in many unrelated user requests. That can cause unintended skill activation, leading the agent to apply this workflow outside its intended scope and potentially override more appropriate skills or inject irrelevant guidance into user sessions.

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: The skill description defines applicability using a very broad set of concepts like work-productivity, self-improving, self, improving, and proactive, without clearly stating exclusion criteria. This ambiguity increases the chance of accidental invocation and misrouting, especially in systems that use description text for retrieval or auto-selection.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The default prompt is broad and conversational, using generic phrases like 'help me' and a long natural-language description rather than a narrowly scoped activation phrase. In systems that support prompt-based routing or invocation, this can cause unintended activation in unrelated conversations, pulling the skill into contexts where it may influence actions or outputs unexpectedly.

Vague Triggers

High

• Confidence: 97% confidence
• Finding: Enabling implicit invocation without narrow trigger constraints allows the skill to activate automatically based on vague or overlapping user intent. Because this skill is framed as proactive and self-improving, accidental invocation is more dangerous: it could insert itself into many workflows, shape decisions, or encourage autonomous behavior outside the user's explicit request.

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The trigger sentence begins with a very generic phrase ('Help me ... practical help') that overlaps with normal user conversation and can cause the skill to activate when the user did not explicitly intend to invoke it. In an agentic environment, overly broad activation increases the chance of inappropriate context injection, workflow hijacking, or confusing responses by routing unrelated requests into this skill.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: This trigger pattern is also too open-ended ('I need a practical workflow for ... practical help') and lacks clear boundaries separating intended use from ordinary requests about workflows or productivity. Because the skill is positioned broadly around self-improving and proactive work, accidental activation is more likely and could misroute benign user requests into an autonomous planning pattern the user did not ask for.

VirusTotal

64/64 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.