Security audit

Clear Prompt Engineering

Security checks for vulnerabilities and agentic risk

Overview

This is a simple prompt-improvement skill with broad automatic activation wording, but it does not request tools, credentials, persistence, network access, or file access.

Install this if you want the agent to proactively help rewrite vague prompts. Be aware it may trigger more often than desired and may use Chinese template labels unless you instruct your agent to keep prompt suggestions in your preferred language.

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 (3)

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The activation criteria are broad enough that the skill may trigger on many normal user messages that are merely somewhat underspecified. In an agent system, unintended automatic invocation can override normal handling, cause prompt rewriting without consent, and create reliability or instruction-following issues across unrelated tasks.

Natural-Language Policy Violations

Medium

Confidence: 88% confidence
Finding: Several core principles and the prompt template are presented in Chinese, while the surrounding document is in English, and the skill does not state that users can choose their preferred language. This creates an implicit language constraint that may conflict with policy requiring user opt-in or documented justification for locale-specific behavior.

Vague Triggers

Medium

Confidence: 96% confidence
Finding: The statement that the skill 'activates automatically when detecting vague input' lacks boundaries, thresholds, and disallowed contexts. This can lead to pervasive interception of user requests, producing unwanted reformulation behavior and increasing the chance that the agent misroutes or transforms tasks that should be handled directly.

Static analysis

No suspicious patterns detected.