ClawHub
Back to skill

Security audit

AI Test Strategy Architect

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-only testing assistant with one ambiguous workflow phrase, but its behavior is otherwise disclosed, scoped, and purpose-aligned.

Installers should treat the generated tests and CI snippets as reference material. Review them before running locally, replace placeholders safely, and avoid using real production credentials in examples.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The execution-boundary statement at L050-L052 explicitly says the skill only outputs reference code and documents, and 'does not execute tests'. However, the Quick Test Generation Workflow includes 'VALIDATE: Run tests, fix failures' at L290, which describes the skill as performing execution-oriented actions that the document elsewhere disclaims.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.