Security audit

跨渠道任务收件箱助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese-language workflow for organizing user-provided cross-channel task exports, with cautious rules around credentials, authorization, paid actions, and result checking.

Install this only if you are comfortable using a Chinese-language workflow and sharing selected task/message exports or redacted materials within the stated scope. Do not provide passwords, tokens, verification codes, cookies, or full identity documents, and require explicit approval before uploads, paid model use, sending messages, deleting data, or changing external systems.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
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
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 99% confidence
Finding: The skill’s declared purpose is cross-channel task ingestion and normalization, but the described behavior shifts into validating artifacts, receipts, hashes, and offline result structure instead of performing the stated workflow. This mismatch is dangerous because users or orchestrators may grant trust, data access, or approvals based on the declared business purpose while the actual workflow processes unrelated artifacts, creating room for misuse, hidden data handling, or bypass of expected review boundaries.
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.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The display name, description, and default prompt all force Chinese-language interaction, but the file provides no indication that this skill is region-specific or that users can opt into another language. Under the language/locale policy, a forced language without user choice or justification is a natural-language policy violation.
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’s operational instructions, headings, and user-facing guidance are all presented in Chinese, which can impose a specific language on users or operators without any stated opt-in. The policy allows fixed language only when user choice is offered or the locale restriction is clearly justified, neither of which appears here.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The only user-facing instruction in this file is written in Chinese: "空值供用户按实际任务填写，不填密码、Token、验证码、Cookie或完整证件信息。" This creates a language-specific constraint without any opt-in, alternative language, or documented regional justification, which matches the locale/language policy concern.
Content: No source excerpt is available for this finding.