ClawHub
Back to skill

Security audit

Task Development Workflow

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed development workflow guide, not executable code, and its Git/Trello/PR actions fit its stated purpose.

Install this if you want a strict development workflow that uses task tracking, branches, pull requests, reviewer notifications, and approval gates. Be prepared to provide access or direction for external tools such as Trello and your Git hosting service when you actually want those steps performed.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
1. Present a detailed plan with task breakdown
2. Keep tasks small and focused
3. **Wait for explicit approval** before starting
4. No implementation without approval

## Phase 3: Task Tracking Setup
Confidence
75% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Static analysis

No suspicious patterns detected.