Security audit

Bug Investigation

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward frontend bug-investigation guide with no executable code, persistence, or hidden high-impact behavior.

Safe to install for frontend debugging workflows. Be mindful that it may activate on general debugging language, and provide sanitized repro data, test accounts, logs, and screenshots instead of real credentials or private production data.

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 (4)

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The trigger phrases are broad enough to match routine debugging language such as '排查 bug', '定位问题', and '调试', which can cause the skill to activate in many ordinary frontend support conversations. Overbroad activation increases the chance of unintended invocation, context capture, or workflow takeover when a more specific or safer skill should have been used.

Natural-Language Policy Violations

Medium

Confidence: 87% confidence
Finding: The file is written primarily in Chinese and presents the workflow and output template in Chinese, but it does not state that language selection should follow user preference. Because the description does not offer opt-in or bilingual output guidance, it may violate language/locale policy expectations for user choice.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: This markdown file defines activation scenarios using generic phrases like "定位问题", "不知道哪里错了", and broad symptom descriptions such as errors, request failures, or abnormal interactions. Without clearer constraints or exclusion examples, the skill could match many ordinary support conversations beyond the intended frontend bug-investigation scope.

Natural-Language Policy Violations

Low

Confidence: 82% confidence
Finding: The user-facing natural-language content is written entirely in Chinese, which can amount to forcing a specific language without opt-in under the stated policy. The file does not indicate that the skill is region-specific or that users may choose another language.

Static analysis

No suspicious patterns detected.