Security audit

ifly-text-proofread

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Chinese proofreading tool that sends user-selected text to iFlytek's remote API, with the main caveat that users should treat submitted documents as shared with that service.

Install only if you are comfortable sending the text you proofread, including any file passed with --file, to iFlytek's remote service using your iFlytek credentials. Avoid using it for confidential, regulated, or personal documents unless your organization permits that vendor and data flow.

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 93% confidence
Finding: The skill documentation indicates capabilities that require environment variable access, file reading, and outbound network access, but it does not declare any explicit tool scope or permissions boundary. That mismatch can cause the agent to use broader capabilities than a reviewer or user expects, increasing the risk of unintended secret access or data exfiltration.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill is designed to send user-provided text to a remote third-party API for proofreading, including potentially sensitive official-document content, but the markdown does not clearly warn users that their text leaves the local environment. In a proofreading context, users may paste confidential, regulated, or personal information, so omission of a transmission/privacy warning materially increases the chance of unintentional data disclosure.

Missing User Warnings

Medium

Confidence: 97% confidence
Finding: The script sends the full user-supplied text to a third-party proofreading API, but the CLI does not provide an explicit disclosure or confirmation that content leaves the local environment. Because this skill is specifically intended for official-document proofreading, inputs may contain sensitive, regulated, or internal information, creating a real confidentiality and compliance risk if users assume processing is local.

Natural-Language Policy Violations

Low

Confidence: 83% confidence
Finding: The description says the skill is for proofreading Chinese text and official documents, which imposes a language-specific constraint. The file does not explicitly present this as a user-selectable option or justify the restriction as a documented region- or compliance-specific requirement.

Natural-Language Policy Violations

Low

Confidence: 79% confidence
Finding: The usage examples, descriptions, and output strings are oriented to Chinese-language input and behavior, but the file does not explicitly state that the tool is region- or language-specific or offer any opt-in choice for locale. Under the stated policy, forcing a specific language without user choice can be a natural-language policy concern.

Static analysis

No suspicious patterns detected.