ClawHub
Back to skill

Security audit

Ephemeral Engineering

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow, self-contained engineering report tool builder with clear safety warnings and no hidden code, network behavior, persistence, or privilege requests.

Before installing, understand that this skill may be selected for a range of engineering calculator, check, and evaluation-letter requests. Generated tools should be treated as drafts only and independently verified, especially because the skill is intended for engineering deliverables.

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
96% confidence
Finding

The skill's invocation guidance is extremely broad and includes many generic engineering and document-generation requests, which can cause the agent to auto-select this skill even when the user did not explicitly ask for it. That increases the chance of misrouting normal requests into a specialized code-generating workflow, potentially producing authoritative-looking engineering deliverables outside the intended scope or without adequate user confirmation.

Content

No source excerpt is available for this finding.