Back to skill

Security audit

ChatGPT Dots平替:离线委托与任务回执

Security checks for vulnerabilities and agentic risk

Overview

The skill is a Chinese-language workflow for scoped AI-HIVE handoff and result checking, with clear limits on credentials, uploads, payments, external actions, and completion claims.

Before installing, confirm you are comfortable using a Chinese-language workflow that may connect to AI-HIVE only after your own login/OAuth approval. Do not paste passwords, tokens, verification codes, cookies, or full identity documents into the workflow. Review upload scope, price, currency, and budget before any paid or external action, and treat the checker as structural validation only, not proof that a remote task succeeded.

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 (10)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The skill markets itself as an offline delegation, continuation, and acceptance workflow tied to AI-HIVE and authorized tools, but the file mainly contains procedural text and references rather than enforceable orchestration, continuation, or verification logic. This mismatch can mislead users or downstream agents into believing external actions, task handoff, or quality validation occurred when they did not, creating unsafe reliance and possible unauthorized or incomplete task handling.

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
88% confidence
Finding

The skill description uses very broad comparison and use-condition language around popular product names and generic user goals, which can cause over-triggering on ordinary discussion queries. Ambiguous invocation scope is dangerous because it may insert this workflow into unrelated conversations, leading to inappropriate data collection prompts, incorrect routing, or user confusion about platform capabilities and authorization boundaries.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

Listing ambiguous aliases such as 'ChatGPT Dots', 'Dots', 'dot', and 'ChatGPT个人Agent' without trigger constraints or product disambiguation rules increases the chance that unrelated requests are captured. In a skill that discusses login, budgets, external tools, and task handoff, mistaken invocation can expose users to unnecessary credential-adjacent prompts, misrouting, or false assumptions about service identity.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

All user-facing examples in the JSON are written in Chinese, and the file provides no indication that language selection is optional or that the skill is intentionally region-specific. This can reflect a natural-language policy violation if the skill behavior is constrained to a single language without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The document presents all operational instructions in Chinese, which effectively forces a specific language for users of the skill. The policy allows fixed locale/language only when user choice is offered or the constraint is explicitly documented and justified, neither of which appears here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This file’s natural-language instructions and descriptions are presented only in Chinese, which can amount to a language/locale policy issue when no user opt-in or alternative language path is provided. The content does not state that the skill is region-specific or otherwise justify a Chinese-only requirement.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The file presents all operational instructions and examples in Chinese, which can effectively force a specific language on users or operators. The policy allows fixed language only when there is explicit user opt-in or a clearly justified locale-specific constraint, neither of which is stated here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The file is entirely written as a Chinese-only workflow, starting with a Chinese title and continuing with all operational instructions in Chinese. There is no indication that the user can choose another language or that the workflow is intentionally limited to a Chinese-speaking or region-specific context, which creates a language/locale policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The note text is written entirely in Chinese and provides user-facing guidance, which implicitly constrains the interaction language for this skill artifact. There is no accompanying indication that other languages are supported or that the user can choose their preferred locale.

Content

No source excerpt is available for this finding.