Work Productivity Weather Current Workflow Helper

• Outcome: Pass
• Latest audit: Jul 29, 2026 · 3:46 AM UTC
• Version: 0.20260729.110214

Overview

This is a documentation-style workflow helper with broad activation wording, but it does not request privileged access, persistence, credentials, or unsafe actions.

Install only if you want a general helper for weather-style workflow planning and skill maintenance. Be aware it may activate too easily because implicit invocation is enabled with broad keywords; users who manage routing should narrow the triggers or invoke the skill explicitly.

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 (12)

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The trigger sentence is broad, natural-language-like, and likely to match ordinary user requests unrelated to this specific skill. That can cause unintended activation, routing user input into the wrong workflow, increasing the chance of inappropriate actions, confusion, or accidental processing under the wrong assumptions.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The keyword list mixes very generic terms such as 'api', 'key', 'required', 'users', and 'bug fix' with broad invocation guidance, making the activation scope ambiguous. In an agent ecosystem, this can lead to over-triggering on commonplace requests and unintended use of the skill in contexts where its workflow is irrelevant or unsafe.

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The trigger phrase examples are extremely broad and include generic language such as 'Help me' and 'I need a practical workflow', which can match ordinary user requests unrelated to this skill. This can cause unintended invocation, routing confusion, and accidental exposure of the skill in contexts where it was not explicitly requested, reducing reliability and potentially interfering with safer or more appropriate skills.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The invocation guidance lacks precise boundaries and mixes broad categories like 'api', 'key', 'required', and 'users' with common workflow language, making the skill easy to trigger accidentally. In an agent ecosystem, ambiguous routing can lead to incorrect tool selection, degraded task handling, and unpredictable chaining into workflows the user did not intend to run.

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The manifest description uses very broad activation terms like 'practical workflow, artifact, checklist, analysis, or implementation support' combined with common topics such as 'api' and 'work-productivity'. This can cause the skill to activate for many unrelated user requests, leading to unintended routing, instruction interference, and increased exposure of the skill's behavior in contexts where it is not appropriate.

Vague Triggers

High

• Confidence: 97% confidence
• Finding: The trigger keyword list includes highly generic words such as 'api', 'key', 'required', 'users', and 'bug fix', which are common across many unrelated conversations. In an agent ecosystem, such broad triggers can cause frequent misfires, hijack routing from more appropriate skills, and create unsafe prompt-scope expansion when the skill is applied outside its intended domain.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The example trigger phrases are framed as broad conversational requests and mostly repeat generic requirement language without clarifying when the skill should and should not be selected. This increases ambiguity for invocation systems and users, making accidental activation more likely and reducing confidence that the skill is being applied in the correct context.

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The trigger keyword list includes very common terms such as "current," "api," "key," "required," and "users," which are likely to appear in many unrelated prompts. This can cause accidental invocation of the skill, leading to prompt routing confusion, incorrect assistance, or unexpected exposure of the skill's instructions in contexts where it was not intended to run.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The example trigger phrases are broad, natural-language requests like "Help me..." and "I need a practical workflow..." that do not meaningfully distinguish this skill from many other tasks. Such generic activation examples reinforce over-broad matching behavior and increase the risk of unintended or inappropriate skill activation during normal conversation.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The default prompt is extremely broad and composed of common-language terms like 'help me' plus a long generic description, which increases the chance of accidental or overly permissive invocation. In a skill with implicit invocation enabled, this can cause the agent to route unrelated user requests into this skill unexpectedly, expanding attack surface and enabling prompt-routing abuse or unintended actions.

Vague Triggers

Medium

• Confidence: 96% confidence
• Finding: Enabling implicit invocation without strict trigger constraints allows the platform to auto-select this skill based on ambiguous user language. Because the skill targets broad domains like productivity, weather, workflows, APIs, checklists, and implementation support, the lack of guardrails makes misinvocation more likely and can expose users to unintended tool behavior or security-relevant prompt injection pathways.

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The trigger phrases are so broad and awkwardly truncated that they can match ordinary user requests or incidental text, causing the skill to activate outside its intended scope. Over-broad activation increases the chance of prompt-routing mistakes, irrelevant skill invocation, and unintended handling of unrelated user tasks, which is a real safety and reliability issue for agent systems.

VirusTotal

64/64 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.