Description-Behavior Mismatch
- 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
Security audit
Security checks for vulnerabilities and agentic risk
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.
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。
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.
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.
Without declared permissions the skill's intent is opaque and cannot be validated.
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.
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。
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.
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 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.