ClawHub
Back to skill

Security audit

qa-shift-right

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-style QA skill for production validation planning, with one visible unpinned companion-skill install command users should verify before running.

Before running the optional `npx` install command, verify the package/source and prefer a pinned version or trusted commit. For the skill's production QA guidance, only apply chaos experiments, monitoring changes, and user-data collection with explicit organizational authorization, rollback plans, and privacy compliance checks.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The skill instructs users to install a package via npx skills add Kokxi/qa-test-skills without pinning an exact package/version. This creates a supply-chain risk: npx may fetch the latest available package or resolve changing content, so a compromised publisher account, replaced package, or malicious update could cause users to execute unreviewed code on their machines.

Content

No source excerpt is available for this finding.