ClawHub
Back to skill

Security audit

Bouncer

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for Bouncer operations, but it needs review because its setup instructions include running an unverified remote installer.

Review the installer path before use. Prefer installing the oo CLI through a verified package or documented installer with integrity checks, and only approve Bouncer write or delete actions after checking the exact payload and target.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (2)

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

The skill instructs the agent to install software by piping a remotely fetched script directly into bash, which executes unverified code from the network without integrity or authenticity checks. If the install endpoint, transport, or upstream distribution is compromised, this can lead to arbitrary code execution on the host running the skill.

Content

Scanner excerpt · SKILL.md (reported line 67)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The description says to use this skill for ANY Bouncer request and whenever a task involves Bouncer, which is an overly broad trigger surface. That can cause the agent to invoke the skill on loosely related prompts and, because the skill includes write and destructive actions, increase the chance of unintended state-changing operations without sufficiently narrow routing criteria.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.