Back to skill

Security audit

读者反馈改稿待办

Security checks for vulnerabilities and agentic risk

Overview

The skill provides a narrowly scoped workflow for organizing supplied writing feedback, with no evidence of harmful behavior.

Provide only feedback and chapter summaries you are comfortable sharing with your agent. Before using the documented npx installation command, review the installer and repository revision; neither is pinned.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (8)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

所提供代码仅包含技能安装命令,没有实现反馈去重归组、章节定位、优先级排序或缺项检查。安装说明可以是配套文档,但不能证明被安装技能的实际行为与描述一致;就当前唯一可见的命令而言,其直接行为与声明的编辑辅助用途不同。本判断不推断远程技能的内容或安全性。

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding

Although this command invokes an installation CLI rather than an MCP server, npx skills can download and execute an unpinned package version. If a future release or its dependencies are compromised, a user following the installation instructions could execute attacker-controlled code; this is a conditional supply-chain risk, not evidence that the skill is malicious.

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 · README.en.md (reported line 19)May include surrounding context.

md
## License and source note

This is an original Chinese workflow. It only consulted the purpose of [story-skills feedback-triage](https://github.com/danjdewhurst/story-skills/blob/main/skills/feedback-triage/SKILL.md); no text or code was copied. Licensed under [MIT-0](LICENSE).

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 · README.md (reported line 36)May include surrounding context.

md
## 来源与许可证

本 Skill 为原创的中文工作流与样例;仅参考 [story-skills 的 feedback-triage 用途说明](https://github.com/danjdewhurst/story-skills/blob/main/skills/feedback-triage/SKILL.md),未复制其内容或代码。许可证见 [MIT-0](LICENSE)。

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

Medium
Category
MCP Rug Pull
Confidence
87% confidence
Finding

The documented installation command invokes an unpinned npm package through npx, potentially downloading and executing a changing package version with the invoking user's permissions. Although the finding incorrectly describes this as an MCP server reference, the underlying dependency-integrity concern is real: a compromised future release could execute malicious code. This is a conventional, user-initiated installation instruction, not evidence of malicious intent or automatic execution by the skill.

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.

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 script generates promotional graphics and an icon, a capability outside the stated feedback-to-action-list purpose.

Low
Category
Excessive Agency
Confidence
96% confidence
Finding

The script reads an illustration, renders hard-coded promotional text, and writes assets/promo-1600x900.png and icon-512.png. These image-generation operations serve promotional packaging rather than organizing supplied feedback, identifying affected chapters, or prioritizing revision tasks, and are not declared in the manifest.

Content

No source excerpt is available for this finding.