ClawHub
Back to skill

Security audit

diff-analysis

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed markdown-only workflow for analyzing diffs and does not include hidden execution, persistence, data exfiltration, or destructive behavior.

Before installing, understand that this skill may activate for broad change-related requests. It appears safe for diff and release-note workflows, but users who want tighter behavior may narrow the trigger phrases.

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 (1)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger keywords and auto-load conditions are broad enough that this skill may activate in loosely related contexts such as generic mentions of 'diff', 'changes', or 'risk assessment'. Unintended activation can cause the agent to load unnecessary instructions and influence workflows that did not actually request this skill, increasing the chance of scope confusion or inappropriate downstream actions.

Static analysis

No suspicious patterns detected.