ClawHub
Back to skill

Security audit

Write Better Tests

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward testing-guidance skill that does not install code, access credentials, or create persistence.

Reasonable to install if you want stricter test-writing discipline. Be aware that it encourages focused test runs and temporary red-green proof changes, so review the final diff to confirm only intended code and test changes remain.

SkillSpector

Vulnerability Patterns
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The description says to use the skill when Codex is 'adding, editing, selecting, reviewing, or explaining tests in any repository,' and the body adds 'whenever test quality matters.' Those conditions are extremely broad and overlap with ordinary development discussion, without clear boundaries for when the skill should not activate.

Session Persistence

Medium
Category
Rogue Agent
Content
description: Use when Codex is adding, editing, selecting, reviewing, or explaining tests in any repository, including mocks, fixtures, snapshots, CI validation, regression coverage, TDD/red-green proof, or readiness claims. Enforces behavior-first test design so tests catch real regressions instead of merely passing the current implementation.
---

# Write Better Tests

Use this skill whenever test quality matters. The goal is not "more tests"; the goal is tests a skeptical maintainer would trust.
Confidence
60% confidence
Finding
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Static analysis

No suspicious patterns detected.