Back to skill

Security audit

ITIL 5 Manager

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only IT service management advisory skill with no evidence of code execution, credential access, persistence, or hidden behavior.

Installers should be aware that common IT support phrases may invoke this skill unintentionally. Treat its output as advisory guidance and verify process, financial, legal, and regulatory recommendations against local organizational policy.

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 (17)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The README says the skill is triggered by keywords such as 'incident management', 'problem management', 'change management', and 'service desk'. These are broad domain terms that can appear in ordinary IT conversations, and the file does not provide constraints, context, or negative examples clarifying when the skill should or should not activate.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The invocation section lists broad phrases such as 'it service management', 'incident management', 'change management', and 'service desk' without any constraints or exclusion examples. These are generic workplace terms that could appear in ordinary discussions, making unintended skill activation more likely.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger list includes broad phrases such as 'it service management', 'incident management', 'change management', and 'service desk', which can overlap with ordinary user requests in general IT support contexts. This can cause the skill to activate unintentionally, increasing the chance that users are routed into this skill when they did not explicitly request it, leading to confused-deputy behavior or unexpected influence over responses.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger list includes very broad phrases such as 'incident management', 'change management', 'service desk', and 'it service management' that are common in ordinary enterprise IT discussions. This can cause unintended invocation of the skill in routine conversations, leading to surprise activation, context hijacking, or the model responding with this skill’s framing 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
93% confidence
Finding

The trigger phrases are generic ITSM terms such as 'incident management', 'change management', and 'service desk', which are likely to appear in ordinary user conversations without an explicit intent to invoke this skill. This can cause accidental activation, unwanted context injection, or the skill taking over responses in situations where the user only wanted general discussion, reducing reliability and potentially exposing users to irrelevant or unintended guidance.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list includes generic phrases such as 'incident management', 'change management', and 'service desk' that are common in ordinary IT conversations. This can cause unintentional activation of the skill in contexts where the user did not explicitly intend to invoke it, increasing prompt-surface exposure and the chance of irrelevant or unsafe context mixing.

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 generic phrases such as 'incident management', 'problem management', 'change management', 'service desk', and 'it service management' that commonly appear in ordinary enterprise conversations. This can cause unintentional invocation or routing of user requests to this skill, increasing the chance of inappropriate activation, context leakage across workflows, or confusing/unsafe automated behavior in environments that rely on trigger matching.

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 generic phrases such as 'incident management', 'change management', 'service desk', and 'it service management' that commonly appear in ordinary IT conversations. This can cause unintended activation of the skill outside explicit user intent, leading to prompt hijacking opportunities, irrelevant responses, or accidental exposure of the skill's specialized instructions in unrelated workflows.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger list includes broad phrases such as 'incident management', 'change management', 'service desk', and 'it service management' that commonly appear in ordinary enterprise support conversations. This can cause unintended activation of the skill in contexts where the user did not explicitly request it, increasing the chance of irrelevant guidance, context capture, or policy bypass through accidental routing.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger list includes broad, common phrases such as 'service desk', 'incident management', and 'change management' that are likely to appear in ordinary IT discussions. This can cause unintended invocation of the skill, leading to irrelevant guidance being injected into conversations and creating prompt-routing confusion or policy bypass opportunities in multi-skill environments.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The file name and heading indicate an English-specific variant ('README.en.md'), but the document does not state that language selection is optional or explain why English is required. This can be interpreted as a locale constraint without documented user opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

Todo el contenido orientado al usuario está presentado únicamente en español y no indica que el idioma sea opcional o configurable. Según la política de idioma/locale, debe evitarse imponer un idioma específico sin elección del usuario, salvo justificación documentada.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The file presents the skill entirely in French and does not indicate that language selection is optional or limited to a French-specific deployment context. Because the policy requires avoiding fixed language or locale behavior without user opt-in or justification, this is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
64% confidence
Finding

This file mixes Japanese documentation with English-only trigger phrases like "it service management" and "service desk" without clarifying whether users may interact in Japanese, English, or choose their preferred language. That can create an implicit language constraint without documented opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

All user-facing natural-language content in this file is presented in Portuguese, but the document does not state that the skill is region- or language-specific nor does it offer an opt-in choice for other languages. This can violate language/locale policy when users are not explicitly given a language preference.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
64% confidence
Finding

该文件整体以简体中文呈现,但未声明这是可选本地化文档,也未提示用户可选择其他语言。若该技能面向通用用户而默认强制单一语言,可能与要求提供语言选择或用户选择权的组织策略不一致。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

This markdown file is entirely written in English and does not mention any option for alternative languages or locales. Under the stated policy category, content that implicitly forces a specific language without user opt-in can qualify as a natural-language policy violation.

Content

No source excerpt is available for this finding.