Security audit

小说家 — 网文写作全流程技能

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Chinese fiction-writing skill that stores project notes locally for continuity, with no executables, network behavior, or deceptive capability found.

Install only if you are comfortable with the skill creating and updating local memory files for each writing project. Review or delete memory/{项目名}/ files if you do not want prior drafts, character notes, or plot-tracking state reused later.

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 (4)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill explicitly instructs the agent to write user-derived content into local memory/{项目名}/... files and frames it as automatic behavior, but it does not require explicit user consent or clearly disclose that data will be persisted on disk. This creates a privacy and integrity risk because users may provide sensitive drafts, ideas, or personal content without realizing it will be stored and reused across later interactions.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: This workflow directs the agent to read persistent memory files and later update plot-tracking state without any disclosure of retention, reuse, or potential exposure of previously stored data. Hidden or assumed persistence can surprise users and cause unintentional cross-session data reuse, especially if multiple projects or sensitive drafts are handled in the same environment.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill instructs the model to append a hidden tracking card to memory/{项目名}/plot_tracking.md, explicitly marking it as hidden from the main output. Hidden persistence is riskier than ordinary storage because the user is not given transparent visibility into what metadata about their content, character states, or future expectations is being retained.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The instructions explicitly require 中文语感 and prescribe Chinese-specific stylistic constraints. This is a natural-language policy issue because it forces a particular language/locale behavior without opt-in or a documented region-specific justification.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.