Back to skill

Security audit

story:网文工具箱路由

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious because a scanner reports that network mode exposes unauthenticated workspace read, overwrite, and deletion APIs; the overall review is incomplete.

Treat this as a review-needed skill, not as a finding that its author is malicious. Before installing, consider whether you need it and whether its network-mode workspace access is acceptable; review the update package and its version before approving updates. The scan was partial: 7 of 9 components were fully scanned, and two were only partially inspected, so the evidence does not establish that all behavior is safe.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/dashboard-server.mjs
Finding

Network mode exposes unauthenticated workspace read, overwrite, and deletion APIs

Content
View full analysis

Impact

Reachable attackers can disclose supported text files and overwrite or permanently delete existing editable files within the selected workspace.

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (6)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 129)May include surrounding context.

md
2. 从当前已加载的 `story` skill 目录定位 `scripts/dashboard-server.mjs`,不要硬编码仓库路径、

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, network, shell.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 156)May include surrounding context.

md
用户问“有没有新版本”“检查更新”“升级”时执行。**先报告版本,是否安装由用户决定。**

1. **当前版本**:读本 skill 同目录的 `VERSION` 文件;缺失则视为未知。本 skill 在写作项目里(如项目下的 `skills/`、`.agents/skills/`、`.zcode/skills/`)时,读到的是项目副本的版本。
2. **最新版本**:优先 `gh release view --json tagName,name,url -R zenstory-ai/oh-story-claudecode` 取 `tagName`;无 gh 用 `curl -fsS --max-time 5 https://api.github.com/repos/zenstory-ai/oh-story-claudecode/releases/latest` 取 `.tag_name`(jq 或 grep)。查不到 → 告知"暂时拉不到最新版本,可手动看 [Releases](https://github.com/zenstory-ai/oh-story-claudecode/releases)",不报错。
3. **比较**:当前版本已知时,去掉 `v` 前缀按语义版本比较(major.minor.patch);未知时只展示最新稳定版,不判定是否已最新。`gh release` 默认取 latest 稳定版,不含 pre-release。
4. **告知**:
   - 已最新 → 「已是最新版 vX.Y.Z」。

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

The update workflow invokes an unversioned executable through npx skills, allowing package resolution to select code that has not been reviewed or pinned. A compromised resolved package could execute with the user's privileges; requiring update consent reduces unexpected execution but does not establish package integrity. This is a package-execution supply-chain issue, not an MCP-server configuration issue.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

This finding duplicates the unpinned npx skills execution issue on the same line rather than identifying an independent vulnerability. If a malicious package version is resolved during an approved update, it could execute code with the user's privileges, potentially accessing local manuscripts and credentials.

Content

No source excerpt is available for this finding.

Generic routing keywords can activate writing-tool workflows for unrelated requests.

Low
Category
Trigger Abuse
Confidence
90% confidence
Finding

The routing table includes everyday phrases such as “看看有没有问题” (check whether anything is wrong), “初始化” (initialize), and “搜一下” (search), then instructs the agent to invoke matching skills directly. Although the skill is described as a fiction-writing toolbox, these entries do not explicitly require a writing-related request or provide exclusions for unrelated review, initialization, or search tasks.

Content

No source excerpt is available for this finding.