Back to skill

Security audit

小说简介与封底文案

Security checks for vulnerabilities and agentic risk

Overview

The skill coherently generates Chinese book blurbs, with an ordinary installation dependency risk from its unpinned installer.

Verify the CLI and repository before using the README installer, preferably selecting reviewed versions. Review generated blurbs for factual accuracy and accidental spoilers before publishing.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (7)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

所提供内容的直接行为是技能安装,而声明描述的是文案生成。两者的主要用途不同,且代码没有展示读取故事信息、遵守禁剧透要求或输出指定长度文案的实现。此判断仅针对提供的命令,不推断远程技能的具体行为。

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

The installation command invokes an unpinned npm CLI through npx, which can download and execute a changing package version with the user's privileges. A compromised package release could therefore execute malicious code during installation, although nothing in this file indicates malicious intent. The finding's MCP-server label is inaccurate: this is an installation-time dependency risk, not evidence of an MCP server.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding

The installation command uses npx skills without a pinned version, allowing npm to resolve and execute a changing package version when no suitable local version exists. A compromised package release could execute code with the installing user's privileges, although this is a conditional installation-time supply-chain risk, not evidence of malicious behavior or an MCP server reference. The skill's text-generation purpose does not require such execution during ordinary use, which limits exposure to users who follow the installation instructions.

Content

No source excerpt is available for this finding.

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

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.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · sources/attribution.md (reported line 4)May include surrounding context.

md
# 参考来源

- [danjdewhurst/story-skills](https://github.com/danjdewhurst/story-skills)(访问于 2026-10-04):仅核对其“submission”类写作 Skill 的用途边界,未复制源码、结构或文案。
- [submission/SKILL.md](https://github.com/danjdewhurst/story-skills/blob/main/skills/submission/SKILL.md)(访问于 2026-10-04):仅作公开用途参考。上游仓库许可证以其仓库文件为准;本仓库的原创文本以 MIT-0 发布。

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · LICENSE (reported line 12)May include surrounding context.

text
permit persons to whom the Software is furnished to do so.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,
INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A
PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE

The skill requires Chinese-language output without offering a language choice or explicit opt-in.

Low
Category
Output Handling
Confidence
90% confidence
Finding

The instruction explicitly requires converting the user's story information into Chinese blurbs, reinforced by the description on L03. Although Chinese output is advertised, the skill does not offer a language choice or explain why a fixed output language is necessary.

Content

No source excerpt is available for this finding.