Security audit

Iflytek Text Proofread

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward iFlytek proofreading skill that sends user-provided Chinese text to iFlytek using the user's API credentials.

Install only if you are comfortable sending the text you proofread to iFlytek's external service under your own iFlytek account. Avoid submitting confidential, regulated, or sensitive documents unless your organization approves that 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 (7)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The README describes a proofreading tool backed by the iFlytek API but does not clearly warn users that submitted text is transmitted to an external third-party service. Because this skill is intended for official-document proofreading and may process sensitive or confidential Chinese text, users could unknowingly send regulated, private, or internal content off-platform, creating privacy, compliance, and data-handling risk.
Content: No source excerpt is available for this finding.

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 94% confidence
Finding: The skill advertises and documents capabilities that require environment-variable access, file reading, and outbound network access, but it does not declare any explicit tool scope or permissions boundary. This can cause the host or reviewer to underestimate the skill's access needs, reducing transparency and increasing the chance that sensitive local files or secrets are exposed during execution.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The skill processes arbitrary user-supplied text by sending it to iFlytek's external API, but the description does not clearly warn users that their content leaves the local environment. Users may submit confidential documents, official materials, or regulated text without informed consent, creating privacy, compliance, and data-handling risk.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill sends user-provided text to a third-party iFlytek proofreading API, but the CLI flow does not provide an explicit user-facing notice or consent checkpoint before transmission. This is risky because users may input sensitive official-document content, personal data, or confidential internal material under the assumption that processing is local.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 78% confidence
Finding: The description specifies proofreading for Chinese text and the README is entirely written in Chinese, but it does not explicitly present this as an opt-in language choice or explain a justified locale-policy constraint. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 83% confidence
Finding: The description says to use the skill when the user wants to proofread or correct Chinese text, which imposes a language constraint. The file does not explicitly present this as a user-selectable limitation or justify it as a locale-specific tool, creating a potential language/locale policy issue under the stated rules.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Low

Category: Not specified by scanner
Confidence: 76% confidence
Finding: The skill’s stated purpose is Chinese text proofreading, but the implementation requires and reads three environment variables containing service credentials. While this is a common integration pattern, access to process environment secrets is a capability beyond text-processing itself and is not described in the manifest text.
Content: No source excerpt is available for this finding.

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: scripts/text_proofread.py:108