Security audit

Work Productivity Agent Browser Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only workflow helper with overbroad activation wording but no evidence of hidden execution, data access, persistence, or destructive behavior.

This skill is reasonable to install if you want lightweight workflow help for Agent Browser-style tasks. Be aware that its broad triggers and implicit invocation setting could make it appear in unrelated browser or automation conversations; prefer explicit invocation or tighten the triggers if precise routing matters.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (12)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill description is broad enough to match many common user requests such as browser, automation, or workflow help, which can cause unintended invocation outside its intended niche. Over-broad activation increases the chance that this skill intercepts requests better handled by more specific skills, leading to incorrect guidance, confused routing, or unsafe automation assistance in the wrong context.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The keyword list contains highly generic terms like "browser," "automation," "cli," and "bug fix," which are likely to collide with many unrelated requests. In an agent ecosystem, this can cause frequent misfires and over-selection of this skill, potentially exposing users to irrelevant or risky workflow advice when a safer or domain-specific skill should respond instead.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The description says to use the skill whenever a user mentions broad categories like work-productivity, browser, headless, or automation, which covers a large portion of normal agent requests. Such ambiguous activation criteria can hijack unrelated conversations, causing incorrect tool selection and making downstream safety and task handling less predictable.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
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 tasks. This can cause the skill to activate outside its intended scope, leading to prompt collision, unintended workflow steering, and reduced reliability of agent behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger phrase is so broad and generic that it can match ordinary user language unrelated to this specific skill, causing the skill to activate unexpectedly. In an agent system, overbroad activation can route sensitive or irrelevant tasks into the wrong workflow, increasing the chance of unsafe automation, poor task handling, or prompt-surface abuse through unintended invocation.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger sentences are extremely broad and partially malformed, making it easy for unrelated user requests containing generic terms like 'workflow', 'browser', or 'help me' to activate this skill unintentionally. In an agent system, ambiguous activation can route tasks into the wrong capability set, increasing the chance of unsafe browser automation guidance, context confusion, or unintended execution paths.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger phrases are broad enough to match common words like 'browser', 'automation', or generic requests for a 'practical workflow', which can cause unintended skill activation. In an agent ecosystem, overbroad activation increases the chance that this skill is invoked in the wrong context, leading to inappropriate guidance, workflow confusion, or unsafe automation steps being suggested for tasks the user did not intend.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The example trigger phrases are malformed, truncated, and do not establish clear activation boundaries, which makes invocation behavior ambiguous. Ambiguous trigger examples can lead implementers or routing logic to infer overly permissive matching patterns, increasing unintended activation and reducing predictability of skill selection.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The default prompt contains a very broad invocation phrase tied to common terms like work-productivity, browser, automation, and practical help, which can cause the skill to activate in routine conversations unrelated to the user's intent. In combination with agent-style workflow assistance, this increases the chance of unintended prompt injection, context hijacking, or unauthorized steering of browser-oriented tasks.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: Enabling implicit invocation without tightly scoped triggers or exclusion rules allows the skill to be auto-selected in a wide range of benign user requests. Because this skill is oriented toward browser and automation workflows, unintended activation could influence actions, recommendations, or downstream agent behavior in contexts where the user did not ask for this capability.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 79% confidence
Finding: The file explicitly labels English and Chinese instruction variants, but does not state how the user's preferred language is selected or whether language choice is optional. That can create a locale-policy concern if the skill defaults users into a language without clear opt-in.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The file is presented as a Chinese README, but substantial user-facing content and trigger text remain in English. This can impose a language expectation on users without documenting a choice or opt-in, which is a natural-language policy concern under the language/locale rule.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.