Security audit

Error Message Improver

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill for improving error messages, with no executable code or credential handling, though its activation wording is broader than necessary.

Installers should be aware that this skill may activate for general debugging or support requests because its triggers are broad. It is otherwise low-risk: it is documentation-only and does not run code, install dependencies, read credentials, persist state, or modify the system by itself.

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 (12)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The manifest description is extremely broad and includes generic terms like work-productivity, debugging, user feedback, support, workflow, checklist, analysis, and implementation support. In agent-routing systems, this can cause the skill to activate for many unrelated requests, creating prompt-scope hijacking risk where this skill intercepts tasks outside its intended niche and influences outputs unexpectedly.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger keywords are broad and ambiguous, especially terms such as debugging, support, troubleshooting, and user feedback, which commonly appear in many unrelated user requests. This increases the likelihood of over-triggering, causing the skill to be selected in contexts where it is not appropriate and potentially altering agent behavior or crowding out safer, more relevant skills.
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 broad enough that ordinary user phrasing could activate the skill without strong scoping, which increases the chance of unintended invocation. While this README does not contain directly dangerous behavior, loose activation boundaries can cause the agent to apply this workflow in contexts where it is not the best or safest fit.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: This trigger pattern is vague and lacks operational boundaries, so it may match many unrelated requests and cause accidental skill selection. In an agent ecosystem, ambiguous routing can degrade reliability, produce irrelevant outputs, or override a more appropriate specialized skill.
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 enough to match common, non-specific user requests, which can cause the skill to activate outside its intended scope. In an agent system, this increases the chance of prompt routing errors, inappropriate tool/skill selection, and unintended processing of unrelated user input.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 81% confidence
Finding: 文件名和内容表明该技能以 zh-CN 版本提供，但文档中未说明是否允许用户选择其他语言，或该语言限制是否有明确的区域性理由。按规则，未提供用户语言/区域选择的强制性语言设定属于自然语言策略问题。
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger keywords are broad, generic terms like work-productivity, debugging, support, and troubleshooting that commonly appear in ordinary conversations. This can cause unintended skill activation, routing user requests into this skill when they did not explicitly want it, leading to prompt hijacking of the interaction flow, irrelevant guidance, or reduced reliability of agent behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The example trigger phrases begin with highly generic formulations such as 'Help me' and 'I need a practical workflow', which overlap with normal user assistance requests. In systems that learn or match from examples, this increases the chance of accidental invocation and misclassification, potentially diverting unrelated tasks into this skill and degrading security-sensitive routing decisions.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The default prompt is phrased so broadly that the skill may be invoked for a wide range of loosely related user requests without clear boundaries or user intent confirmation. This increases the chance of unintended activation, causing the agent to inject workflow guidance or error-message transformations into contexts where it was not explicitly requested.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: Enabling implicit invocation without a tightly defined activation scope allows the skill to run automatically based on weak semantic matches rather than explicit user consent. In a broad support/debugging context, this can lead to over-triggering, prompt interference, and unexpected influence over agent responses across many normal workflows.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger phrase begins with a very generic everyday request pattern ('Help me ...'), which increases the chance that ordinary user messages will invoke this skill unintentionally. In an agent environment, overly broad activation can route unrelated conversations into the wrong workflow, causing misexecution, confusion, and unsafe automation chaining if downstream actions rely on the skill being intentionally selected.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 80% confidence
Finding: This file is a Chinese-localized user document and the listed files emphasize separate English and Chinese variants, but this document itself does not offer user language choice or explain a justified locale restriction. Under the language/locale policy, forcing a specific language without opt-in can be a policy concern.
Content: No source excerpt is available for this finding.