Back to skill

Security audit

Work Productivity Ontology Typed Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a simple workflow-guidance skill with overly broad activation wording, but it does not run code, persist data, or request sensitive access.

Before installing, be aware that this skill may activate on general workflow or knowledge-graph wording more often than expected. It appears low risk because it only provides guidance and contains no executable components or sensitive-access instructions.

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 (12)

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger sentence begins with a broad everyday phrase ('Help me') tied to a long, generic requirement description, which creates weak activation boundaries for routing. In agent or tool-selection systems, ambiguous triggers can cause this skill to activate for unrelated requests, leading to misrouting, prompt-context contamination, or unintended workflow execution.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The second trigger sentence ('I need a practical workflow for ...') is also highly generic and could match many ordinary planning or productivity requests unrelated to this specific skill. In a multi-skill environment, this increases the chance of accidental invocation and unreliable routing, which can degrade safety and correctness by applying the wrong workflow to the user's intent.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrases are broad, repetitive, and match generic productivity or workflow requests, which can cause the skill to activate outside its intended scope. In an agent ecosystem, over-broad activation can route unrelated user tasks into this skill, producing incorrect guidance, overshadowing safer or more appropriate skills, and increasing the chance of unintended downstream actions.

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 generic enough to match ordinary user requests about workflows, bug fixes, or hardening, which can cause the skill to activate unintentionally. Over-broad activation increases the chance of prompt hijacking, inappropriate routing, or execution in contexts the user did not explicitly request.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill description and usage guidance are broad enough to match many ordinary requests involving workflows, analysis, implementation support, or productivity topics. In an agentic routing system, this can cause unintended activation, leading the wrong skill to shape outputs, introduce irrelevant instructions, or bypass a more appropriate specialized skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The keyword list includes highly generic terms such as 'typed', 'knowledge', 'graph', 'structured', 'creating', and 'bug fix', which are common across many unrelated tasks. These vague triggers increase false activations and misrouting risk, especially in systems that auto-select skills based on keyword overlap rather than deeper intent understanding.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The example trigger phrases are vague, repetitive, and framed in everyday language that does not clearly distinguish this skill from general help requests. Ambiguous examples can train users or automated selectors to invoke the skill in situations outside its intended scope, reducing reliability and potentially causing unsafe or low-quality task handling.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill description defines applicability in very expansive terms, covering broad domains and generic requests for workflows, checklists, analysis, or implementation support. Because it does not clearly distinguish in-scope versus out-of-scope cases, the skill may be selected for many ordinary productivity or knowledge-related tasks that do not actually require this specialized ontology workflow helper.

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 and include common terms such as "knowledge", "graph", "structured", and "creating", which can overlap with many unrelated user requests. This can cause the skill to activate in contexts where it is not the best match, leading to incorrect routing, irrelevant guidance, or suppression of more appropriate skills.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The default prompt is framed as a generic natural-language sentence and includes broad terms like 'help me' and common productivity concepts, which increases the chance of accidental or overly broad invocation. Because implicit invocation is enabled, this overlap can cause the skill to activate in unrelated conversations and inject its workflow guidance unexpectedly, creating prompt-routing and scope-control risk rather than direct code-execution risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The file lists separate English and Chinese documentation variants, but the README does not explain how the skill selects language or whether the user can choose their preferred locale. This can create an implicit language/locale policy without explicit opt-in or guidance.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

This file is presented as a Chinese README, but key descriptive and usage content is written in English, including the main requirement and workflow description. That can impose a language experience inconsistent with the apparent locale of the document without stating that users may choose their preferred language.

Content

No source excerpt is available for this finding.