Security audit

Multi-Dimensional Novel Evaluation System

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only novel review rubric with no evidence of hidden commands, data access, persistence, or unsafe behavior.

Reasonable to install for creative writing feedback. Only provide manuscript text you are comfortable sharing with the active agent or model, and note that one scoring phrase is untranslated but does not create a security risk.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
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 (1)

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: Line L053 contains the untranslated Chinese phrase "起伏感" within otherwise English guidance. This imposes a mixed-language experience without user opt-in or documented justification, which can violate language/locale policy expectations.
Content: No source excerpt is available for this finding.