Back to skill

Security audit

小说投稿梗概包

Security checks for vulnerabilities and agentic risk

Overview

The skill coherently turns supplied novel material into Chinese submission summaries, with no evidence of hidden access or harmful actions.

Review generated facts and character counts before submitting. If using the documented installer, prefer a reviewed, pinned CLI version and source revision.

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
  • 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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (7)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

声明描述的是直接处理小说资料并生成投稿材料,而代码片段实际提供的是外部技能安装命令。安装可能是使用该技能的前置步骤,但仅凭此命令无法验证被安装技能是否实现所声明功能,也不能将其未展示的行为视为已实现。就所提供代码而言,实际行为与声明用途存在实质差异。

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
85% confidence
Finding

The installation command invokes the unpinned npm package skills through npx, potentially downloading and executing a release that changes over time. A compromised release could execute code with the installer's permissions, although this README provides no evidence of an actual compromise or automatic execution. The finding incorrectly calls this an MCP server reference; the supported concern is installation-time supply-chain exposure.

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 example uses an unpinned npm CLI, npx skills, so following it can download and execute a changing package version with the user's permissions. A compromised upstream release could therefore execute malicious code; however, this is an optional, documented installation step rather than automatic skill execution, and the file does not actually reference an MCP server.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: 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.md (reported line 6)May include surrounding context.

md
本 Skill 的中文说明、流程、样例与脚本均为原创实现。仅参考以下公开资源来核对“投稿资料整理”这一用途,未复制其源码或文案:

- [story-skills repository](https://github.com/danjdewhurst/story-skills)(访问用途:投稿相关 Skill 的目录语境)
- [submission Skill](https://github.com/danjdewhurst/story-skills/blob/main/skills/submission/SKILL.md)(访问用途:投稿资料工作流的高层参考)

本仓库采用 MIT-0 许可证;参考链接不代表其内容被纳入本仓库。

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 specifies Chinese-language synopses without an explicit language choice or opt-in.

Low
Category
Output Handling
Confidence
89% confidence
Finding

The description fixes the synopsis output language as Chinese without offering a language choice. It does not explicitly justify this restriction through a Chinese-language submission requirement or other locale-specific constraint.

Content

No source excerpt is available for this finding.