ClawHub
Back to skill

Security audit

商品包装单位单价对照

Security checks for vulnerabilities and agentic risk

Overview

This skill compares user-provided package prices without purchasing, accessing accounts, or transmitting data.

Provide confirmed prices, quantities, dates, currencies, and shipping terms, and check the results before buying. If using the README installation command, review the installer and source revision because neither is pinned.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • 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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The supplied command performs skill installation, which is materially different from calculating and validating package unit prices. It contains no handling of prices, quantities, units, currencies, dates, shipping terms, or purchase requirements. Although its location in README.en.md suggests it may be setup documentation, the supplied executable behavior is installation; the installed skill’s actual functionality cannot be established from this snippet.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The only supplied executable behavior is an external skill installation command. Although its target name matches the declared topic, the command does not implement or demonstrate the promised calculations, validation, or outputs. This assessment is limited to the supplied chunk; the installed skill's behavior is unknown.

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

The installation command invokes the npm package skills through npx without pinning a version, so installation can execute a changing dependency rather than a reviewed release. If that package or its publishing account is compromised, following the command could execute attacker-controlled code with the user's permissions. This is an installation-time supply-chain risk, not an MCP-server reference as the detector claims; the ordinary comparison functionality and absence of automatic execution reduce 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
88% confidence
Finding

The installation command uses npx skills without a pinned version, allowing npm to resolve and execute a package version that has not necessarily been reviewed. If that package or its distribution channel is compromised, following the installation instructions could execute malicious code with the installing user's privileges. This is a supply-chain hardening issue rather than evidence of malicious intent or an MCP server reference; the skill's narrow calculation purpose does not require this additional trust.

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

Static analysis

No suspicious patterns detected.