ClawHub
Back to skill

Security audit

justify

Security checks for vulnerabilities and agentic risk

Overview

This is a code-review guidance skill that inspects local git diffs and asks for justification of changes, with no hidden execution or data-sharing behavior found.

Before installing, note that this skill may appear in general code-review situations and will push for strict justification of added code and test changes. That is appropriate if you want a quality-gate style reviewer, but you may prefer narrower triggers if you only want it invoked explicitly.

SkillSpector

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

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger list includes broad phrases such as "code-review" and "reviewing completed work before merging or after AI-assisted implementation," which are likely to match routine developer activity rather than a deliberate, narrowly scoped invocation. This can cause the skill to auto-activate too often, injecting prescriptive review behavior into unrelated workflows and creating prompt-surface expansion where repository content may influence agent behavior more frequently than intended.

Static analysis

No suspicious patterns detected.