Back to skill

Security audit

连载前情摘要

Security checks for vulnerabilities and agentic risk

Overview

This skill summarizes supplied Chinese fiction chapters and produces writing notes, with no evidence of hidden access or unrelated actions.

Provide only chapter material you are comfortable sharing with your agent. For installation, copy a reviewed package directory or use a trusted installer version; the documented npx command can execute downloaded code and does not pin versions.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (6)

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

Medium
Category
MCP Rug Pull
Confidence
87% confidence
Finding

The installation command invokes npx skills without a pinned version, allowing a changing registry-resolved package to execute with the installing user's permissions. A compromised future release could therefore execute malicious code; however, this is a conventional, user-initiated installation instruction, not an MCP server reference or evidence of malicious intent.

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 command npx skills add xxjrq/novel-serial-recap-cn can download and execute an unpinned version of the skills CLI, creating a supply-chain risk if the resolved package is compromised. The referenced skill source is also not pinned to an immutable revision, allowing installed content to change. This is an installation-time dependency risk rather than an MCP-server issue; its placement in optional installation instructions, with no evidence of automatic execution or malicious content, reduces immediate 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 command uses npx skills without a fixed version, allowing installation-time execution of a package version that may change or become compromised. Although the detector incorrectly describes this as an MCP server reference, the unpinned executable dependency creates a genuine supply-chain risk. This is an optional, user-invoked installation step rather than automatic execution, and the Markdown-only workflow otherwise provides no evidence of malicious behavior.

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 3)May include surrounding context.

md
# 用途参考

本 Skill 的连载上下文整理用途参考了公开项目 [zenstory-ai/oh-story-claudecode](https://github.com/zenstory-ai/oh-story-claudecode) 中的 [story-long-write](https://github.com/zenstory-ai/oh-story-claudecode/blob/main/skills/story-long-write/SKILL.md)。

本仓库独立编写前情提要、续写记忆卡工作流和样例,不复制外部实现、源码或文案。未纳入该项目的整本书工程流程。本仓库自身采用 [MIT-0](LICENSE) 许可证。

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 SOFTWARE