Security audit

book translate

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward book and long-text translator that reads user-provided content, splits it, translates it, and combines the result.

Installers should treat this as a normal translation skill, but avoid using it for confidential, regulated, or proprietary documents unless they are comfortable with the agent and translation model processing the full text. Users who need other target languages should confirm the skill supports them or adjust the request explicitly.

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
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill explicitly processes entire books, PDFs, and long texts by reading the content and sending chunks to a translation capability, but it does not warn users that potentially sensitive document contents will be transmitted and processed. This creates a real privacy and data-handling risk because users may upload confidential manuscripts, internal reports, or personal documents without informed consent about downstream processing.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The examples and invocation guidance consistently hard-code the target language as Chinese and instruct users to translate books into Chinese. This imposes a specific language/locale behavior without user opt-in or an explicit statement that the skill is intentionally limited to a Chinese-only use case.

Static analysis

No suspicious patterns detected.