Back to skill

Security audit

Work Productivity Proactive Agent Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only workflow helper with no code execution, credential access, persistence, or hidden behavior, though its activation wording is broader than ideal.

Installers should be aware that the skill may activate on vague productivity or task requests. It is best used when explicitly requested for proactive-agent workflow planning, reliability hardening, checklist creation, or adjacent skill design.

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
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
95% confidence
Finding

The trigger phrases are broad, generic, and partially duplicated from the requirement text, which increases the chance that the skill activates in contexts the user did not intend. In an agent ecosystem, ambiguous activation can cause incorrect workflow selection, unintended instruction injection into unrelated tasks, or overreach into user requests that only loosely match terms like 'task', 'transform', or 'needs'.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger phrases are broad, generic terms such as 'task', 'proactive', and 'needs', plus natural-language example prompts that resemble ordinary user requests. This can cause unintended activation of the skill in unrelated conversations, increasing the chance that the agent applies the workflow when not requested and potentially overrides more appropriate skills or causes prompt-routing confusion.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger list is overly broad and includes generic terms such as 'task', 'needs', and 'proactive', which are likely to appear in many unrelated user requests. In an agent-routing system, this can cause unintended activation, making the skill intercept conversations it was not meant to handle and potentially override safer or more appropriate skills.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger list includes very broad everyday terms such as "task", "needs", and "partners", which can cause the skill to activate in many unrelated conversations. Over-broad invocation increases the chance that this skill overrides more appropriate skills or injects workflow guidance where it was not requested, creating prompt-routing and unintended-action risks.

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 requests such as 'Help me...' combined with common productivity terms, which can cause the skill to activate outside its intended scope. In an agent ecosystem, unintended invocation can route user tasks to the wrong workflow, increasing the risk of irrelevant actions, confused delegation, or accidental application of automation in contexts the user did not mean.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest description uses broad activation language like 'Use when a user asks for work-productivity, proactive-agent, proactive, transform, task' without clear boundaries. This increases the chance that orchestrators or maintainers will configure the skill too permissively, leading to accidental invocation on vague or unrelated prompts.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The description says the skill should be used when a user asks for broad categories like work-productivity, proactive, transform, or task, which lacks a clear boundary for when activation is appropriate. This ambiguity can lead to accidental selection in benign contexts and makes routing behavior unpredictable, especially in systems that rely on textual matching.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The default prompt and description are highly broad and generic, covering terms like work-productivity, proactive-agent, transform, task, checklist, analysis, and implementation support. This can cause the skill to match loosely related requests and activate when the user did not clearly intend to invoke it, increasing the chance of prompt-scope overreach and unintended handling of user tasks.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

Implicit invocation is enabled, but the file provides no meaningful activation constraints beyond a very broad skill description. In this context, the combination makes unintended auto-selection more likely, which can route user requests into this skill without sufficiently clear consent or relevance checks.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This trigger remains generic because it relies on everyday wording that could describe many unrelated support requests, making activation scope ambiguous. In a proactive agent setting, ambiguity is more dangerous because the skill is designed to transform and drive workflows, so accidental selection may lead to over-broad assistance, user confusion, or unintended processing of context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
70% confidence
Finding

In this Chinese-language README, core usage content and trigger phrases are presented in English, but the document does not indicate that users may choose their preferred language. That can impose a language expectation without opt-in, which is a natural-language policy concern under the locale/language rule.

Content

No source excerpt is available for this finding.