Security audit

Error Message Improver

Security checks for vulnerabilities and agentic risk

Overview

The skill is a static helper for improving error messages, with no code execution or persistence, though its activation wording is broader than ideal.

Install only if you want an agent helper for rewriting or designing clearer error messages. Be aware it may activate on general debugging or support requests because its triggers are broad; invoke it explicitly for error-message work if your platform allows that.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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: 96% confidence
Finding: The skill description uses very broad routing language such as 'work-productivity,' 'debugging,' 'support,' and 'implementation support,' which can cause the agent to invoke this skill for many unrelated requests. Overbroad activation increases prompt-scope risk by pulling in irrelevant instructions and may interfere with safer or more appropriate skills, leading to misrouting and degraded security boundaries.
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 so broad and awkwardly templated that it can match ordinary user requests about help, workflows, or support rather than an intentional invocation of this specific skill. In an agent system, overly broad activation criteria can cause unintended routing, leading this skill to intercept unrelated prompts and influence outputs in ways the user did not request.
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, natural-language prompts that can match ordinary user requests rather than an explicit opt-in to invoke this skill. That increases the chance of unintended activation, causing the skill to intercept unrelated conversations and influence outputs without clear user intent.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger phrases are generic and broad enough to activate on many ordinary support, debugging, or productivity requests that may not actually need this skill. Over-broad activation can cause unintended routing, prompt hijacking opportunities through loosely matched phrases, and accidental exposure of user context to the wrong workflow.
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 generic operational terms that appear in many benign conversations, so they are likely to cause unintended activation outside the skill's intended domain. In agent systems, imprecise triggers can be abused or can accidentally expand the skill's authority, increasing the chance of context confusion and unsafe workflow selection.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The example trigger sentences are phrased so generally that they normalize invocation from vague natural-language requests rather than specific error-message tasks. While not directly malicious, this can train or bias routing toward false activations, which reduces reliability and may expose users to irrelevant instructions or outputs.
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 and overlap heavily with ordinary support and productivity requests, which can cause the skill to activate outside its intended scope. Over-triggering can steer unrelated conversations into this skill’s workflow, increasing the chance of irrelevant guidance, user confusion, and unintended handling of sensitive troubleshooting content.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The example invocations use generic phrasing that does not meaningfully constrain when the skill should be called. This reinforces ambiguous routing behavior and makes it easier for normal conversation text to be misinterpreted as an activation request.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill enables implicit invocation while providing only a broad, underspecified description of when it should trigger. That can cause the agent to invoke this skill in contexts it was not explicitly requested for, potentially steering user interactions or overriding more appropriate behavior with error-message rewriting assistance.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 72% confidence
Finding: The file lists English and Chinese instruction and guide files, but does not state how language selection is determined or that the user can choose their preferred locale. This can create a locale-policy concern if the skill defaults users into a language without explicit opt-in.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 77% confidence
Finding: This file is presented as a Chinese README, but key user-facing content such as the requirement statement is written in English, and the trigger phrases are also English-only. That can amount to forcing a language/locale without user opt-in or explanation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 78% confidence
Finding: L04 在中文技能描述中嵌入大段英文需求文本与英文标签，可能导致技能在未征得用户同意的情况下输出或依赖特定语言内容。文件未说明是否应根据用户语言偏好切换或提供语言选择。
Content: No source excerpt is available for this finding.