Security audit

Flutter Expert

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward Flutter guidance skill with no executable code, credential use, persistence, or hidden behavior found.

Installers should expect a Chinese-language Flutter assistant that may be invoked for general Flutter requests and gives opinionated guidance around Riverpod, GoRouter, and clean architecture. Review whether those conventions match your project before relying on generated code.

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 (4)

Natural-Language Policy Violations

Medium

Confidence: 83% confidence
Finding: The README presents the skill introduction and adaptation notes entirely in Chinese and explicitly highlights enhanced Chinese annotations and explanations. For a general-purpose skill, this can amount to a language/locale constraint without user opt-in or justification.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The README states the skill will automatically activate for Flutter-related help, which is a broad trigger surface for a high-authority guidance skill. Overbroad activation can cause the agent to invoke this skill in contexts where the user did not explicitly request it, increasing the chance of irrelevant instruction injection, unintended dominance over other skills, or excessive exposure of workspace-specific behavior.

Natural-Language Policy Violations

Medium

Confidence: 83% confidence
Finding: The description is written only in Chinese and presents the skill persona and scope without indicating multilingual behavior or locale constraints. In a mixed-language environment, this can lead to unintended language forcing, degraded usability, and misalignment with user expectations, though it is not a direct security compromise.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The activation guidance is broad: '当用户请求 Flutter 相关帮助时' would match a large class of generic Flutter requests rather than a narrowly scoped capability. Overly broad triggering can cause the skill to override more appropriate system behavior, inject opinionated instructions unexpectedly, or be invoked in contexts the user did not specifically request.

Static analysis

No suspicious patterns detected.