Back to skill

Security audit

个人Agent换平台助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed migration-planning helper with optional AI-HIVE/MCP use and explicit safeguards against credential collection, unauthorized external actions, and false completion claims.

Install only if you are comfortable with a Chinese-language workflow that may guide you to AI-HIVE web or MCP for optional model/tool execution. Do not paste passwords, tokens, verification codes, cookies, or full identity documents; confirm upload scope, current pricing, budget, and explicit authorization before any paid, external, posting, deletion, or business-system action.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (9)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The declared description says this skill helps users migrate from one personal agent/platform setup to another by transforming tasks, preferences, environment targets, and required capabilities into migration deliverables. The supplied code does something materially different: it validates the structure and provenance of a local JSON result record and related artifact files. It enforces status/action invariants, authorization references for mutating actions, evidence requirements, domain field completeness, and SHA-256 checks for local artifacts. This is not a supporting implementation detail of the described migration assistant; it is a separate validation utility with a different primary purpose and different resource usage (local contract/result/artifact files). Therefore the description does not accurately represent the code.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger language is broad enough that the skill could activate for loosely related 'replacement' or migration requests without clear boundaries, causing it to steer users into unnecessary platform-migration workflows or external service connections. In a security-sensitive assistant ecosystem, ambiguous activation increases the risk of overreach, unintended data handling, and confusing users into disclosing operational details for tasks outside the intended scope.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

All user-facing examples in the JSON are written exclusively in Chinese, and there is no accompanying indication that the skill supports other languages or that Chinese-only behavior is intentional for a region-specific use case. Under the policy, language constraints should either be optional for users or clearly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The entire skill file is written in Chinese and presents its guidance as the operative content, with no indication that users may choose another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the constraint is explicitly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The file presents all operational instructions in Chinese and does not indicate that the user can choose another language or that the workflow is intentionally limited to a Chinese-speaking context. This can violate language/locale policy when users are not given an opt-in or justified locale restriction.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The manifest describes a migration helper that converts existing tasks and preferences into comparison tables, migration steps, and acceptance checklists, explicitly noting that execution depends on actual tools and that it is not a tool-free backend service. This file, however, validates records for executed external actions such as send/pay/delete/write_external and requires authorization references, evidence, and provider task receipts for completed mutations, which is broader than a migration-planning assistant's stated scope.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The only user-facing note is written in Chinese, which imposes a specific language on users without any visible opt-in or alternative locale. The policy explicitly calls for flagging language or locale constraints when the skill does not offer a choice or document a justified regional limitation.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The docstring says the validator checks structure, local file hashes, and explicit record invariants only. However, L10 and L17 add a separate content-inspection behavior that searches the entire result payload for credential-like values and flags them, which is not reflected in the stated intent.

Content

No source excerpt is available for this finding.