Security audit

Error Message Improver

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-only helper for improving error messages, with overly broad auto-invocation wording but no evidence of malicious behavior.

This skill appears safe to install for help rewriting or designing clearer application error messages. Be aware that its broad triggers may make it appear for general debugging or support tasks; use it explicitly when the task is about error-message wording or troubleshooting copy.

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: 96% confidence
Finding: The skill description uses broad activation terms such as work-productivity, debugging, support, and practical workflow, which can cause the skill to trigger for many unrelated requests. Over-broad routing is dangerous because it may insert this skill's instructions into contexts where they do not fit, leading to incorrect behavior, prompt collision with other skills, or unintended access to user tasks outside the intended narrow scope of error-message improvement.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger keywords are highly generic and include terms like debugging, support, troubleshooting, and user feedback, which are common across many unrelated skills and user intents. This increases the chance of accidental invocation or priority hijacking, where this skill activates instead of a more appropriate one and influences outputs in unintended contexts.
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 extremely broad and mirror ordinary user requests for help, which can cause the skill to activate in many unrelated contexts. Over-broad activation increases the chance the agent routes sensitive, security-relevant, or general support queries into this skill unexpectedly, creating prompt-routing confusion and possible policy bypass through unintended tool selection.
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 natural-language prompts such as 'Help me' and 'I need a practical workflow', which can cause the skill to activate in many ordinary support or productivity conversations without clear user intent. In an agent environment, overbroad invocation increases the chance of unintended routing, context capture, or the skill influencing tasks outside its narrowly intended scope.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The example trigger phrases are framed in broad everyday language and directly mirror a general business need rather than a narrowly scoped task. Even without malicious intent, such examples train routing toward over-activation, making the skill more likely to match vague user requests and interfere with correct skill selection.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The trigger keywords are very broad and overlap with common conversational topics like debugging, support, and user feedback. In an agent routing context, this can cause accidental activation of the skill on unrelated requests, leading to inappropriate workflow injection, confused task handling, or exposure of internal templates and behavior where they were not intended.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The example trigger phrases are phrased as generic everyday requests and do not establish clear boundaries for when this skill should be selected. This increases the chance that the orchestrator or user will invoke the skill for loosely related tasks, which can degrade reliability and create unsafe overreach in multi-skill environments.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill enables implicit invocation, but the metadata does not define a narrowly scoped trigger or tightly bounded conditions for when the agent should auto-select it. That can cause the skill to be invoked in broader contexts than intended, potentially exposing unrelated user inputs to this skill and creating prompt-routing or overreach risks.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger sentence begins with a very broad conversational phrase ('Help me ...'), which can cause the skill to activate on ordinary user requests that were not intended to invoke this specific capability. In an agent setting, overly permissive activation increases the chance of accidental routing, prompt confusion, or invocation chaining that exposes irrelevant instructions or alters task handling unexpectedly.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 79% confidence
Finding: Although this is a Chinese README, core user-facing sections such as the requirement description, workflow description, keywords, and trigger phrases are written in English. This can effectively impose a language/locale expectation without explicit user opt-in or explanation.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.