Back to skill

Security audit

品牌叙事

Security checks for vulnerabilities and agentic risk

Overview

The skill provides a coherent brand-strategy workflow, with ordinary installation risks and no evidence of hidden harmful behavior.

The workflow reads relevant brand materials. Before using the README installer, review its source and version; omit -g for project-only installation and -y to retain confirmation prompts.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The supplied command installs a skill rather than analyzing brand strategy or producing the declared narrative deliverables. Although the target skill's name matches the description, global installation is a materially different operation not disclosed by that description. The installed skill's contents are not supplied, so its eventual behavior cannot be verified.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
93% confidence
Finding

The installation command uses npx skills without a pinned version, allowing a changing npm release to execute with the installing user's privileges. Although the detector incorrectly describes this as an MCP server reference, the underlying supply-chain risk is real: a compromised release could execute malicious code, and the skill source is also not pinned to an immutable revision. This is user-facing installation guidance rather than an automatic execution instruction, which limits exposure to users who run the command; there is no evidence of malicious intent.

Content

No source excerpt is available for this finding.