Work Productivity Agent Browser Workflow Helper

• Outcome: Pass
• Latest audit: Jul 24, 2026 · 5:08 PM UTC
• Version: 0.1.0

Overview

This is a documentation-only workflow helper with no hidden execution, but its trigger wording is overly broad and could cause accidental activation.

Before installing, consider narrowing or explicitly invoking this skill so it does not handle unrelated browser, automation, CLI, or bug-fix requests. The artifact itself appears to be guidance-only and low risk, but its current trigger scope is broader than necessary.

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 (9)

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The trigger phrases are broad and partially malformed, covering generic terms like browser, automation, and practical workflow. In agent ecosystems, this can cause unintended invocation in unrelated contexts, leading the wrong skill to run and potentially perform browser or automation-oriented actions the user did not explicitly request.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The trigger phrases are broad enough to match many ordinary requests about browsers, automation, productivity, or workflows, which can cause the skill to activate outside its intended scope. In an agent ecosystem, this increases the chance of unintended delegation, prompt/context hijacking, or the skill influencing tasks the user did not explicitly intend to route through it.

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The trigger keywords are excessively broad for a skill-selection mechanism, including generic terms like "browser," "automation," and "cli" that can match many unrelated requests. This can cause the skill to activate outside its intended scope, increasing the chance of irrelevant guidance, unsafe workflow influence, or overshadowing more appropriate skills in security- or reliability-sensitive contexts.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The example trigger phrases are vague, malformed, and resemble everyday help requests rather than precise activation criteria. Ambiguous examples train or encourage over-triggering behavior, which can lead to accidental invocation of this skill for unrelated user intents and reduce overall routing safety and accuracy.

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The trigger list includes very generic terms such as "browser", "automation", "cli", and "bug fix", which are common across many unrelated requests. This can cause the skill to activate in situations outside its intended scope, leading to prompt hijacking of routing, incorrect tool selection, or accidental disclosure of workflow-specific guidance where another skill should have handled the request.

Vague Triggers

High

• Confidence: 91% confidence
• Finding: The description says to use the skill when a user asks for broad categories like work-productivity, browser, headless, or automation, without clearly limiting the scope to this specific workflow helper. Ambiguous activation criteria increase the chance of unintended invocation, causing this skill to intercept generic requests and potentially override more appropriate, safer, or more specialized skills.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The default prompt uses very broad, generic wording around work productivity, browser workflows, automation, checklists, analysis, and implementation support, which can overlap with many ordinary user requests. Combined with allow_implicit_invocation: true, this increases the chance the skill is invoked when the user did not explicitly request it, causing unintended prompt injection surface expansion and potentially unnecessary access to the skill's instructions or behavior.

Vague Triggers

High

• Confidence: 97% confidence
• Finding: The trigger sentence is an overly broad everyday phrase that can cause the skill to activate for generic requests unrelated to the intended browser-workflow use case. In an agent environment, this can lead to unintended routing, overbroad handling of user requests, and increased exposure to prompt-surface abuse because the skill may be invoked in contexts where its assumptions and safeguards do not fit.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The invocation guidance is underspecified and includes malformed, overly broad examples, which makes it easier for the skill to be selected outside its intended scope. This increases the chance of misrouting and prompt injection adjacency: an attacker or even normal user phrasing could unintentionally trigger the skill and obtain outputs that are irrelevant, unsafe, or bypass more appropriate specialized handling.

VirusTotal

64/64 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.