Back to skill

Security audit

migration-verify

Security checks for vulnerabilities and agentic risk

Overview

This migration-check skill is coherent, but it can inspect and change a user's local agent setup and test artifacts with limited scoping or confirmation.

Install only if you want an agent to perform a broad post-migration audit of your local agent files and tooling. Before running it, confirm the workspace paths, backups, temporary output locations, and whether repair actions such as restoring skills, replacing paths, installing dependencies, rebuilding automation, or deleting test artifacts should require your approval.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger phrases include broad everyday terms such as '体检', '压测', and '全不全', which can cause the skill to activate in unrelated conversations. Because this skill performs extensive environment verification and test execution, accidental activation could lead to unintended system inspection and follow-on file operations in a context where the user did not clearly request them.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The stress-test section explicitly calls for creating and deleting snapshots, documents, packages, and clones, but the skill does not prominently warn the user about these side effects or require explicit consent for destructive cleanup steps. In a migration-validation context, even 'test' deletion can remove the wrong files or artifacts if paths are misresolved, increasing the risk of data loss in a newly moved environment.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The operational instructions and user-facing wording are written entirely in Chinese, including the required briefing text in the workflow. There is no indication that the user can choose another language or that the locale restriction is intentional and justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.