Security audit

Uncertainty Verification

Security checks for vulnerabilities and agentic risk

Overview

This is a simple fact-checking guidance skill with broad but disclosed triggers and no hidden code, persistence, credential use, or destructive behavior.

Install this if you want the agent to be more deliberate about checking facts, numbers, code, and completed operations. Expect it may add extra verification steps or confidence labels in routine technical work; users who do not read Chinese may want a translated version of the instructions.

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)

Natural-Language Policy Violations

Medium

Confidence: 81% confidence
Finding: The description and operating instructions are written entirely in Chinese, and there is no indication that the user can choose another language or that the skill is intended only for a Chinese-language environment. This can violate language/locale policy when a skill implicitly enforces one language without opt-in.

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The front-matter trigger conditions are broad enough to activate the skill after many ordinary assistant tasks, such as generating technical content or code examples. Over-broad invocation can cause unintended post-processing, user-confusing behavior, and expanded attack surface if adversarial content can intentionally trigger the skill in inappropriate contexts.

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The trigger list in the body further broadens activation with ambiguous items like '生成技术内容后' and '完成外部操作后' without defining thresholds or scope. This can make the skill fire in routine interactions, causing unintended execution paths, wasted resources, and potential interference with other skills or workflows.

Static analysis

No suspicious patterns detected.