Security audit

Error Message Improver

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only skill for improving error messages, with no code execution or persistence, but its automatic trigger wording is broader than ideal.

This skill appears safe to install for help improving error messages. Be aware that its broad implicit triggers may make it activate for general debugging or support requests where you did not specifically ask for error-message rewriting.

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 (11)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill description includes broad invocation terms such as work-productivity, debugging, support, and practical workflow, which can match many ordinary user requests unrelated to this specific skill. Over-broad routing increases the chance the skill is invoked in unintended contexts, causing scope hijacking, incorrect delegation, or unreviewed instructions to influence responses more often than intended.
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, support, or error handling without clear intent to invoke this specific skill. That creates a prompt-routing risk where the agent may activate the skill in unintended contexts, causing incorrect handling, scope overreach, or user confusion rather than direct code execution harm.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger sentence begins with very common help-seeking language ('Help me ...'), making activation boundaries too broad for a shared assistant environment. This can cause unintended invocation when a user is speaking generally about support or error-message needs, which may route the conversation into this skill unexpectedly and reduce user control over agent behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger uses broad generic phrasing ('I need a practical workflow for ...') that overlaps with ordinary user requests and lacks a clear boundary indicating when this specific skill should activate. In an agent ecosystem, such ambiguity increases the chance of accidental triggering, misrouting, and unintended disclosure of context to a skill the user did not explicitly 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 extremely generic (for example, 'Help me' and 'I need a practical workflow') and are likely to match ordinary conversation rather than an intentional invocation of this skill. That can cause accidental activation, routing user content into the wrong workflow, and unexpected handling of potentially sensitive troubleshooting or support data.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The file descriptions explicitly separate English and Chinese documentation variants, and this README is written for a Chinese locale without any statement that users may choose their preferred language. Under the policy, locale-specific behavior should be opt-in or clearly justified.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger list uses generic keywords like debugging, support, troubleshooting, and user feedback without boundaries or disambiguation rules. In a skill-selection system, these broad triggers can capture a large volume of unrelated requests, making the skill more likely to activate outside its intended domain and potentially interfere with safer or more appropriate skills.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The top-level description defines activation conditions too broadly and lacks clear boundaries or exclusion criteria. In an agent environment, ambiguous routing can invoke this skill for many loosely related requests, increasing the chance of prompt-surface expansion, misrouting, and unintended influence over responses.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger section uses broad keywords such as work-productivity, debugging, support, and troubleshooting that commonly appear in ordinary conversations. This can cause the skill to activate outside its intended scope, leading to irrelevant instruction injection into unrelated tasks and reducing user control over agent behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill enables implicit invocation, but the metadata does not define a narrow, bounded trigger describing exactly when the agent should auto-select this skill. Because the description is broad and overlaps common support and productivity topics, the skill may be invoked in contexts the user did not intend, causing unsolicited handling of user input and increasing the chance of prompt-routing errors or misuse.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The example trigger phrases are highly generic and can match everyday language with minimal domain specificity. This increases accidental activation risk, though the examples alone are less dangerous than the broader description and keyword list because they are illustrative rather than primary routing logic.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.