ClawHub
Back to skill

Security audit

justify

Security checks for vulnerabilities and agentic risk

Overview

This skill is a markdown-only code review checklist that reads git diffs and asks for justification before changes are merged.

Install this if you want stricter review discipline around AI-assisted code changes. Be aware that its triggers are broad, so it may be invoked during normal code-review conversations; narrowing the trigger phrases would reduce accidental activation.

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
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrase "code-review" is broad and likely to appear in ordinary developer conversation, commit metadata, or workflow descriptions. That can cause accidental invocation of the skill outside the author's intended context, increasing the chance that repository instructions or agent behavior are influenced unexpectedly during routine review activity.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger text "reviewing completed work before merging or after AI-assisted implementation" describes a general situation rather than a precise activation token. Ambiguous activation conditions can make the skill fire whenever an agent infers that broad context, leading to unintended execution during normal development and review flows.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.