ClawHub
Back to skill

Security audit

Production Agent Builder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a markdown-only framework for planning AI agents and does not include code, hidden actions, credential use, persistence, or data access.

Review whether the broad trigger phrases fit your workflow; otherwise this appears safe to install as a planning aid. Any agent you design with it should still gate email, publishing, money movement, data changes, and deletion behind human approval, as the guide itself recommends.

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
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest description says the skill triggers on phrases like "design an agent," "agent architecture," and "agent planning." These terms are fairly broad and could match ordinary conversation about agents or architecture without clearly constraining when the skill should activate, and no negative examples or exclusion conditions are provided.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.