Back to skill

Security audit

栏目写作风格手册

Security checks for vulnerabilities and agentic risk

Overview

The skill provides a clearly scoped editorial workflow, with an ordinary installation dependency caution.

Provide only articles you are comfortable sharing with your agent. Before using the README installation command, review the installer and source revision; prefer reviewed, fixed versions where supported.

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 Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (7)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The supplied command performs skill installation, a materially different operation from the declared editorial-analysis task. No code implementing article analysis, style-guide generation, or requests for clarification is shown. The installed skill might implement those features, but its contents are not supplied and cannot be verified.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The visible command performs skill installation, which is not described in the declared purpose. It does not inspect writing samples, derive style rules, or produce the promised guide and checklist. The installed skill might implement those functions, but its contents are not supplied and cannot be verified from this chunk.

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 is an installation CLI rather than an MCP server, npx skills can download and execute an unpinned package with the invoking user's privileges. A compromised package release could therefore execute malicious code during installation; the explicit, user-initiated installation context reduces exposure but does not eliminate the supply-chain risk. The repository being installed is also not pinned to an immutable revision.

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 35)May include surrounding context.

md
## Source and license

The public [marketingskills repository](https://github.com/coreyhaines31/marketingskills) and its [copy-editing Skill](https://github.com/coreyhaines31/marketingskills/blob/main/skills/copy-editing/SKILL.md) were consulted for business purpose only. This repository contains original instructions and examples and does not copy external prose or source code. 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 48)May include surrounding context.

md
## 来源与许可证

业务用途参考了 [marketingskills](https://github.com/coreyhaines31/marketingskills) 的公开目录及其 [copy-editing Skill](https://github.com/coreyhaines31/marketingskills/blob/main/skills/copy-editing/SKILL.md),本仓库的说明、步骤和示例均为原创,未复制其内容或源码。仓库采用 [MIT-0](LICENSE)。

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

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding

The installation command invokes the unpinned npm package skills through npx, which can download and execute a changing package version with the installing user's privileges. This is a supply-chain exposure rather than an MCP-server issue: a compromised release could execute malicious code, although the README provides no evidence of compromise or automatic execution.

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