Security audit

Error Message Improver

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill for improving error messages, with some overly broad auto-invocation wording but no code execution, data access, persistence, or hidden behavior.

Installers should be aware this skill may be invoked more often than intended because it includes generic triggers like support, debugging, troubleshooting, and work-productivity. It is otherwise low risk: it does not run code, install dependencies, persist state, or access credentials.

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 contains very broad invocation language such as 'work-productivity,' 'debugging,' 'support,' and requests for 'practical workflow, artifact, checklist, analysis, or implementation support,' which can match a large range of unrelated user prompts. This can cause the skill to be invoked outside its intended scope, leading to prompt routing errors, interference with other skills, and reduced reliability of security or policy-sensitive task handling.
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 terms that appear in many normal conversations and technical requests. Because they are not specific to error-message improvement, they increase the chance of unintended invocation collisions, where this skill activates instead of a more appropriate or more tightly controlled skill.
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 broad enough to match ordinary user phrasing about help, productivity, support, or debugging, which can cause the skill to activate outside its intended scope. Over-broad activation can route unrelated conversations through this skill, creating prompt-selection confusion and increasing the chance of irrelevant or unsafe guidance being applied in the wrong context.
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 generic enough to match ordinary user requests about help, workflows, or support, which can cause the skill to activate outside the author's intended scope. Overbroad invocation increases the chance of prompt/skill hijacking at the routing layer, where this skill may 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: 97% confidence
Finding: The trigger phrases are broad and generic enough that the skill may activate for loosely related requests involving debugging, support, or productivity. This can cause unintended invocation, leading the agent to apply the skill in contexts where it is not appropriate and potentially mishandle user intent or expose internal workflows more widely than intended.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The example trigger phrases use ordinary, broad language and effectively teach the router that common requests should activate this skill. While not directly enabling code execution or data exfiltration, they reinforce overbroad matching behavior and make accidental invocation more likely in routine conversations.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The skill description defines activation conditions too broadly, including several high-level categories without clear boundaries. In orchestration systems, this increases the chance of accidental invocation and context mismatch, which may expose irrelevant workflow instructions or interfere with selection of a more appropriate skill.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The trigger keywords are broad and loosely bounded, covering generic topics like work-productivity, debugging, support, and troubleshooting. This can cause the skill to activate in many unrelated conversations, leading to unintended routing, user confusion, or lower-quality assistance when the skill is applied outside its intended scope.
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, but the metadata does not define a narrowly scoped trigger or clear activation constraints. This can cause the agent to invoke the skill in broader contexts than intended, exposing users to unintended prompt routing, confusing behavior, or abuse by adversarial prompts that steer tasks into this skill without explicit user intent.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The activation examples describe the requirement in generic language but do not define when the skill should not be used, leaving trigger boundaries ambiguous. This ambiguity can cause accidental invocation by common speech or adjacent tasks, reducing routing integrity and potentially exposing users to the wrong workflow or output expectations.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 77% confidence
Finding: The README explicitly labels separate English and Chinese instruction files, but this file does not state how the user's preferred language is selected or that language choice is optional. That can create an implicit locale policy without documented user opt-in.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: This file presents the user-facing documentation in Chinese, but there is no visible note in the content offering users a language option or explaining that the locale is intentionally region-specific. Under the stated policy, forcing a specific language without opt-in can be a natural-language policy concern.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.