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 hidden code, credential access, persistence, or destructive behavior.

This skill is reasonable to install if you want an advisory helper for agent-browser workflow planning. Review its broad trigger terms because it may activate for generic browser, CLI, automation, or bug-fix requests where a more specific skill would be better.

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

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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 (10)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The description says to use the skill whenever a user asks for broad categories like 'browser', 'headless', 'automation', or a generic 'workflow, artifact, checklist, analysis, or implementation support'. This ambiguous activation language significantly expands the skill's matching surface and can cause accidental invocation for common requests that do not actually fit the specialized purpose of the skill.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger keywords are very broad (for example, 'browser', 'automation', 'cli', and 'bug fix') and are likely to match many unrelated user requests. This can cause the skill to activate outside its intended scope, leading to incorrect routing, unexpected behavior, and possible interference with more appropriate skills in sensitive automation contexts.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger sentences are broad, awkwardly templated, and include generic terms like practical workflow, browser, and automation that can cause the skill to activate outside its intended scope. In an agent environment, overbroad activation can route unrelated requests into browser-automation guidance, increasing the chance of unintended tool use, user confusion, or unsafe workflow recommendations.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger section uses very broad keywords such as "browser", "automation", and "bug fix", plus generic natural-language trigger phrases. In an agent ecosystem, this can cause unintended skill activation in unrelated conversations, leading the wrong workflow to run and potentially exposing user context or causing unsafe browser-oriented actions to be suggested without clear user intent.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The activation description is ambiguous because it mixes many broad domains ('work-productivity', 'browser', 'automation') with vague conditions like needing a practical workflow or analysis. This increases the chance the skill is selected for requests outside its intended scope, which can degrade safety and reliability by applying the wrong instructions or artifacts to the user's task.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger keywords are very broad, including generic terms like 'browser', 'automation', 'cli', and 'bug fix' that commonly appear in unrelated user requests. This can cause accidental invocation of the skill in contexts where it was not intended, leading to prompt-scope confusion, inappropriate workflow guidance, or overshadowing of more specific skills.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The default prompt uses very broad, everyday trigger terms such as work-productivity, browser, automation, and practical help, which can cause the skill to activate in contexts far beyond the author’s intended scope. Because implicit invocation is enabled, this increases the chance of accidental routing, prompt confusion, and unintended execution of browser-oriented workflows in unrelated conversations.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger sentence is extremely broad and can match ordinary user phrasing unrelated to this specific skill, causing unintended activation. In an agent system, overbroad routing can expose users to the wrong workflow, create prompt-scope confusion, and let a skill influence conversations it was not explicitly selected for.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The invocation phrase is ambiguous because it can be used in contexts broader than the skill's intended purpose, increasing the chance of accidental or adversarial invocation. This is dangerous in multi-skill agents because loosely scoped activation language can hijack task routing and cause the model to apply this skill where another, safer or more relevant skill should be used.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: In this Chinese-language README, key descriptive content is presented in English, which can amount to a language-policy issue when the user is not given any choice of language. The file does not state that English is optional or justified for a specific regional/compliance reason.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.