Back to skill

Security audit

ecommerce-listing-pack

Security checks for vulnerabilities and agentic risk

Overview

The scanners rate this skill benign with high confidence: most security checks were clear, while installation instructions raised a versioning concern and a possible mismatch with its stated purpose.

The verdict is benign, but benign does not mean risk-free. Before installing, consider that the documented installer is unpinned and that the scanner could not confirm whether the installed skill matches the listing-generation purpose. Use a reviewed, version-pinned installer if available, and check the installed skill’s purpose before relying on it.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

The supplied shell commands perform installation, not any of the declared content-generation functions. Although they reference a skill with a matching name, the chunk contains no listing-generation implementation or invocation. This assessment is limited to the supplied commands and does not establish what the installed skill does.

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 documented command invokes an unpinned npm CLI through npx, allowing a changing upstream release to execute with the installing user's privileges. This is a conditional supply-chain risk, not an MCP-server configuration issue or evidence of malicious behavior; the documentation does not itself execute the command.

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 release notes recommend executing an unpinned npm CLI through npx, so users following the instructions can receive a different executable release over time. A compromised upstream release could run code with their privileges; this is an installation supply-chain weakness rather than the MCP-server issue described by the detector.

Content

No source excerpt is available for this finding.