Work Productivity Skillscan Security Workflow Helper

• Outcome: Pass
• Latest audit: Jul 27, 2026 · 9:00 AM UTC
• Version: 0.20260727.80339

Overview

This is a documentation-style workflow helper with no executable code, but its broad implicit triggers may cause unwanted activation.

Before installing, consider narrowing or disabling implicit invocation so the skill only runs when explicitly requested for SkillScan-style security workflow help. The inspected artifact is otherwise a low-impact guidance skill rather than a code-executing or data-accessing package.

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: 95% confidence
• Finding: The trigger sentences are written in broad, natural language that overlaps with ordinary user requests, which can cause the skill to activate unintentionally. In an agent ecosystem, overbroad invocation can route unrelated tasks into this skill, producing incorrect behavior, unexpected security workflow interference, or privilege misuse if the skill is allowed to influence execution paths.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The keyword list includes generic terms such as 'security', 'gate', 'every', 'must', 'pass', 'before', and 'activate', which are common across many unrelated conversations. This increases the chance of accidental invocation or trigger collision with other skills, especially in automated routing systems that rely on keyword matching, leading to unintended task handling and potentially unsafe workflow substitution.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The trigger phrases are broad generic terms like "security", "every", "must", and "bug fix", which can cause the skill to activate for many unrelated requests. In an agent ecosystem, overly broad routing increases the chance of unintended invocation, context hijacking, or the skill influencing tasks it was not meant to handle.

Vague Triggers

High

• Confidence: 96% confidence
• Finding: The skill description says to use the skill for very broad terms like "work-productivity," "security," and generic requests for workflows or checklists, which can cause accidental activation on ordinary user prompts. In an agent system, over-broad routing increases the chance that this skill intercepts unrelated requests, leading to incorrect behavior, policy bypass through misclassification, or unsafe workflow substitution.

Vague Triggers

High

• Confidence: 98% confidence
• Finding: The trigger keyword list includes extremely generic words such as "security," "gate," "every," "must," "pass," "before," and "activate," which are common in many benign prompts. This makes unintended invocation highly likely, and in a multi-skill agent can let this skill preempt more appropriate handlers or distort security-sensitive workflows simply because common words appear.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The example trigger sentences are unnatural, fragmented, and not representative of real user requests, so they fail to establish a clear invocation boundary. Poor trigger examples make routing behavior ambiguous for maintainers and automated systems, increasing accidental activation and making security review of dispatch logic less reliable.

Vague Triggers

High

• Confidence: 96% confidence
• Finding: The trigger keyword list includes very broad everyday terms such as "security", "every", "must", "pass", and "before", which can cause the skill to activate in many unrelated conversations. Over-broad activation creates routing ambiguity and may surface this skill when the user did not intend it, increasing the chance of irrelevant guidance, context hijacking, or bypass of more appropriate skills.

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: The usage condition in the description is broad and ambiguous, saying to use the skill when users ask for several generic topics or need practical workflow support for the requirement. This weak boundary makes accidental invocation more likely and can cause the skill to handle requests outside its intended scope.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The default_prompt contains a very broad invocation phrase built from generic help-seeking terms like 'help me' and common workflow language. In combination with a security/workflow helper skill, this can cause the skill to activate in ordinary conversations where the user did not intend to invoke it, creating prompt-routing confusion and unintended application of the skill’s instructions.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: Enabling allow_implicit_invocation without clear trigger boundaries increases the chance of accidental or over-broad activation. Because this skill is framed as a general productivity/security workflow helper, implicit invocation can unexpectedly insert the skill into unrelated user requests, which may alter behavior, leak context into an unnecessary tool path, or bypass user intent.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The trigger sentences and keywords are broad enough to match common conversational language such as 'help me', 'security', 'workflow', 'every', or 'bug fix', which can cause the skill to activate in situations far outside its intended scope. In an agent ecosystem, this increases the risk of prompt routing errors, unintended invocation, and leakage of irrelevant or sensitive context into the wrong workflow.

VirusTotal

64/64 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.