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, credential handling, persistence, or hidden behavior found.

Install this skill if you want help making application errors clearer and more actionable. Be aware that its broad trigger terms may cause it to appear during general debugging or support requests, so invoke it explicitly when you want error-message wording, troubleshooting copy, or failure-guidance structure.

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 (10)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The skill description uses broad activation language such as work-productivity, debugging, support, and implementation support, which can cause the agent to invoke this skill for many loosely related requests. Overbroad routing increases the chance that the wrong skill handles sensitive or unrelated tasks, leading to unsafe delegation, prompt-scope confusion, or interference with more appropriate security- or domain-specific skills.
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 highly generic and include common terms like debugging, support, troubleshooting, and user feedback, which are likely to appear in many unrelated conversations. This makes accidental or excessive invocation more likely, expanding the skill's effective authority and creating routing ambiguity that can be abused or can simply degrade safe task selection.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger sentence begins with a very broad everyday phrase ('Help me ...'), which can cause the skill to activate during ordinary user requests that were not intended to invoke this specific skill. In an agent environment, over-broad invocation patterns increase the chance of accidental routing, context confusion, and inappropriate application of the skill to unrelated tasks.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger sentences are broad, natural-language phrases that could activate the skill in situations well beyond the intended scope. In an agent ecosystem, vague activation criteria can cause unintended invocation, leading the agent to inject this workflow into unrelated conversations or override more appropriate skills, which is a real security and safety control weakness even without malicious content.
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 broad enough to match ordinary support, debugging, and productivity requests, which can cause the skill to activate in many unintended contexts. Overbroad activation increases prompt-surface area and can route sensitive or unrelated user queries into this skill without clear user intent, creating opportunities for inappropriate handling or data exposure through unnecessary processing.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The example trigger sentences use vague natural phrasing and do not establish firm boundaries for when the skill should or should not activate. Ambiguous examples train permissive matching behavior, which can result in unintentional invocation on ordinary help requests and reduce the reliability of skill selection.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger keywords are broad and overlap heavily with common support and debugging requests, which can cause the skill to activate outside its intended scope. Mis-triggering is dangerous because it can steer unrelated conversations into a predefined workflow, causing incorrect guidance, user confusion, or suppression of a more appropriate skill or baseline response.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill enables implicit invocation while describing its use case in very broad terms ('work-productivity, error messages, debugging, user feedback, support'), which increases the chance the agent will auto-select it in contexts the user did not clearly intend. Over-broad auto-routing can expose user content to an unnecessary skill, create surprising behavior, and expand the attack surface for prompt injection or data handling mistakes across many unrelated conversations.
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 is a zh-CN README, but key descriptive content such as the demand statement and target users is written in English. This can amount to an implicit language policy issue because the skill does not indicate that users can choose their preferred language or that mixed-language output is intentional.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 77% confidence
Finding: 该文件是 SKILL.zh-CN.md，其内容整体以简体中文呈现，但未见提示用户可选择其他语言或说明仅在用户明确要求中文时适用。根据规则，若技能以自然语言强制特定语言/区域设置且无用户选择机制，可能构成语言或 locale 政策问题。
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.