ClawHub
Back to skill

Security audit

Bun Workspace Optimizer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain Markdown guide for analyzing Bun workspaces and does not include hidden execution, persistence, or data exfiltration behavior.

Installers should expect this skill to read workspace package metadata and suggest dependency, build, test, CI, and migration changes. Review any proposed file edits, lockfile removal, package manager migration, or install command before applying it, especially in non-Bun projects.

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
89% confidence
Finding

The skill's trigger phrases are very broad and can cause it to activate for generic repository or performance-related requests without clear boundaries, increasing the chance an agent will apply workspace-analysis behavior in contexts the user did not intend. Because the skill recommends inspecting repository files and running discovery commands, over-broad invocation can lead to unnecessary access to project metadata and configuration, or unsafe command suggestions in unrelated contexts.

Content

No source excerpt is available for this finding.