Security audit

Work Productivity Humanizer Remove Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

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

Installers should treat this as a low-risk workflow helper, but should narrow or explicitly invoke it if possible because its generic triggers could activate during unrelated writing, editing, review, or bug-fix requests.

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 (11)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger phrases are so generic that this skill can activate on ordinary requests about writing, editing, reviewing, bug fixes, or removing signs/generated text, causing unintentional invocation outside its intended scope. In an agent ecosystem, overbroad routing increases the chance that unrelated user tasks are captured and processed by this skill, which can lead to incorrect actions, prompt-scope confusion, and unsafe cross-context behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill description is framed so broadly that it can match many ordinary productivity or implementation requests unrelated to a narrowly defined task. Overbroad activation increases the chance this skill is invoked in the wrong context, causing prompt/skill routing confusion and potentially steering users into unintended workflows.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 99% confidence
Finding: The trigger keywords are extremely generic terms such as 'remove,' 'writing,' 'text,' and 'bug fix,' which are likely to appear in many unrelated conversations. This makes accidental invocation highly likely and can let the skill intercept broad categories of requests it was not specifically designed to handle.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger examples include generic natural-language phrasing that could match ordinary user requests far beyond the intended scope of this skill. In an agent system, overly broad activation can cause unintended invocation, leading the skill to run in unrelated contexts and potentially influence outputs, workflows, or downstream actions without the user explicitly selecting it.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger sentence is phrased as a very broad natural-language request, making accidental activation likely during ordinary conversation. In an agent/skill-routing environment, this can cause the wrong skill to run on unrelated user input, which may lead to unintended transformations or workflow execution without clear user intent.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This trigger uses a generic helper-style phrase ('I need a practical workflow for ...') that overlaps with normal user requests, increasing the chance of unintended skill selection. Because the skill is positioned as a workflow helper, broad matching can silently redirect user tasks into this skill when the user did not explicitly request it.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The example trigger sentences rely on vague, reusable phrasing like 'help me' and 'I need a practical workflow,' without enough limiting context. These examples encourage invocation patterns that overlap with normal user language, reinforcing misrouting and over-activation risk.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The description defines activation using a wide set of loosely scoped needs like practical workflow, artifact, checklist, analysis, or implementation support, combined with generic topic words. This ambiguity makes the invocation boundary unclear, so the skill may be selected in contexts far beyond its intended job-to-be-done, creating reliability and prompt-routing risk.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger list includes very broad everyday terms such as "writing", "text", "editing", "reviewing", and "bug fix", which can cause the skill to activate for many unrelated requests. This increases the chance of accidental routing, where users receive workflow guidance from the wrong skill and security-relevant tasks may be handled with an unintended prompt or process.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The default prompt contains broad, generic phrasing ('help me' and a long natural-language task description) that can overlap with ordinary user requests and trigger this skill unintentionally. Because implicit invocation is enabled, accidental activation could route unrelated conversations into this skill, causing prompt hijacking of user intent, unexpected behavior, or inappropriate disclosure of context to the skill.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The activation guidance is ambiguous and does not define firm boundaries for when the skill should or should not run. This increases the risk of accidental routing collisions with unrelated productivity, writing, editing, or bug-fix requests, which can degrade reliability and cause the agent to apply the wrong workflow to user tasks.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.