Back to skill

Security audit

flutter-architecture

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Flutter architecture guide that may scaffold project folders when asked, with no evidence of hidden execution, data access, persistence, or exfiltration.

Before installing, expect this skill to guide Flutter MVVM architecture decisions and, when you explicitly ask for scaffolding, create project folders under lib/. Review the proposed module names and paths before letting it modify an existing project.

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
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
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description is written as a hard requirement in Chinese for the skill's usage context, with no indication that the user may choose another language or locale. The rule covers language or locale policy violations when a skill forces a specific language without opt-in.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill explicitly instructs the agent to create directories directly under lib/ when certain trigger phrases are used, but it does not require an explicit confirmation step or warn that it will modify the filesystem. In an agent context, that can cause unintended project changes, especially if a user is asking for architectural guidance rather than authorizing write operations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

The title and entire document are written as a prescriptive team standard in Chinese, and the file presents the conventions as mandatory rather than offering a language or locale option. Under the stated policy, forcing a specific language without opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.