ClawHub
Back to skill

Security audit

BugPack View Bug

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently helps view local BugPack bug details and does not show evidence of hidden code, persistence, or external data transfer.

Install this only in workspaces where showing BugPack bug details is appropriate. Bug details may include internal routes, source file paths, browser/device metadata, and screenshots, so avoid using it in shared or untrusted sessions unless that information is safe to reveal.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This skill explicitly retrieves and displays detailed bug data from a local service, including screenshots, environment information, related file paths, and local-style upload paths, but it does not warn the user that potentially sensitive internal information may be exposed. That omission can lead to unintentional disclosure of proprietary code locations, filesystem structure, or sensitive visual data contained in screenshots, especially when the skill is used in shared or less-trusted contexts.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.