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 language, but it does not contain code, persistence, credential access, external execution, or destructive behavior.

Installers should be aware that the skill may activate too easily on ordinary writing or editing requests. Prefer explicit invocation by skill name, and consider narrowing its trigger keywords before relying on implicit routing.

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 (13)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The manifest description says to use the skill when a user asks for broad categories like 'work-productivity' or needs a 'practical workflow, artifact, checklist, analysis, or implementation support,' which are generic conditions matching many normal requests. In skill-routing systems, this ambiguity can cause over-selection of the skill, leading to misrouting, prompt interference, and unsafe or low-quality task handling in contexts unrelated to this skill's actual specialty.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger keyword list is overly broad and includes common words like 'remove', 'signs', 'generated', 'writing', 'text', and 'reviewing' that are likely to appear in unrelated user requests. This creates a real risk of unintended skill invocation, causing the agent to apply this workflow outside its intended scope and potentially override more appropriate skills or inject irrelevant behavior into benign editing tasks.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger keyword list includes very common terms such as 'remove', 'generated', 'text', 'writing', 'editing', and 'reviewing', which can match many unrelated user requests. This creates an over-broad activation surface where the skill may be invoked outside its intended context, causing unintended instruction injection into unrelated workflows and reducing routing reliability.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger sentence is broad enough to match ordinary user language unrelated to a tightly scoped skill invocation, which can cause the skill to activate in unintended contexts. In an agent environment, overly permissive routing can lead to inappropriate handling of requests, confusion of user intent, or accidental execution of workflows the user did not explicitly want.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger sentence is phrased as a broad natural-language help request rather than a narrowly scoped invocation, which increases the chance the skill will activate during ordinary conversation when the user did not intend to call it. In agent ecosystems, unintended invocation can route user input into the wrong workflow, causing confusing behavior, prompt interference, or execution of actions under an irrelevant skill context.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: This trigger is a generic request for a 'practical workflow' and lacks clear semantic boundaries, making accidental matches likely across many unrelated user prompts. Because the skill is framed for broad work-productivity and editing use cases, the context makes over-triggering more dangerous by expanding the set of normal conversations that could incorrectly activate it.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger phrases are broad, generic request templates that can match ordinary user language rather than a narrowly scoped skill invocation. This can cause unintended activation of the skill in unrelated conversations, leading to confusing behavior, incorrect workflow selection, or accidental handling of requests the skill was not meant to process.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The example trigger phrases use everyday language such as 'Help me' and 'I need a practical workflow,' which are not unique indicators of this skill and are likely to occur in many unrelated conversations. If the routing or matching system relies on these examples, the skill may be invoked spuriously, increasing the chance of context confusion and unnecessary prompt injection into routine tasks.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The enablement condition in the description is vague and mixes broad topic words with generic requests for 'workflow, artifact, checklist, analysis, or implementation support'. Ambiguous activation criteria increase the chance that the skill is selected for loosely related requests, which can override better-matched skills or introduce unintended behaviors into benign tasks.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The sample trigger phrases use generic help-seeking language like 'Help me' and 'I need a practical workflow', which trains or encourages invocation from ordinary requests that lack strong context. Combined with the broad keywords elsewhere, these examples amplify false activations and can cause the skill to capture unrelated conversations.
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, everyday activation language tied to generic terms like work-productivity and practical help, which can cause the skill to be invoked in contexts far beyond its intended scope. Because implicit invocation is enabled, this increases the chance of unintended routing, prompt collisions, and user requests being steered into this skill without clear user intent.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: This trigger uses ambiguous broad phrasing that lacks a precise boundary for when the skill should engage, increasing the chance of false-positive activation. Because the skill is framed as a general helper for practical workflows, accidental matching could reroute many normal productivity requests into this specific skill, reducing predictability and potentially causing unsafe or irrelevant outputs.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 71% confidence
Finding: This Chinese README contains substantial English prose for core descriptive content, which can impose a language preference on users reading the zh-CN variant. The file does not indicate that users can choose their preferred language or that the mixed-language content is intentional.
Content: No source excerpt is available for this finding.