ClawHub
Back to skill

Security audit

fullstack-engineer

Security checks for vulnerabilities and agentic risk

Overview

This is a broad but straightforward full-stack engineering guidance skill with no hidden execution, persistence, or data access behavior in the inspected artifact.

Installers should understand this is a general-purpose engineering skill: review generated code carefully for sensitive areas such as authentication, payments, database migrations, and deployment before applying changes.

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
95% confidence
Finding

The skill description is triggered by very broad terms like 'frontend, backend, databases, devops, api design,' which can cause the agent to invoke this skill in many loosely related contexts without clear boundaries. Overly broad routing increases the chance of inappropriate skill selection, leading to excessive authority, unintended code generation, or handling of sensitive infrastructure tasks when a narrower specialized skill would be safer.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.