Security audit

Cloudflare Browser Run

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for using Cloudflare Browser Run through OOMOL, but its setup instructions include unverified remote scripts executed directly on the user’s machine.

Review the installer path before using this skill. Prefer installing the oo CLI through a verified package or a downloaded installer with a pinned version and checksum/signature verification, and only connect the Cloudflare Browser Run account you intend this skill to use.

A.I.G

Vulnerability Patterns

Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
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
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

Findings (1)

T03 · Remote Payload Retrieval and Execution

Error

Location: SKILL.md:60
Finding: Unverified Remote Installer Downloaded and Executed Directly
Content: View full analysis
Remediation: View remediation
oo-install.sh" | sha256sum --check - bash oo-install.sh ``` The placeholder URL and checksum must be replaced with an official version-pinned artifact and a checksum obtained from a separately authenticated source. Equivalent signature and integrity verification should be required for the PowerShell installer. ]]>

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: 98% confidence
Finding: The skill instructs users to install software via curl ... | bash, which executes a remote script directly without prior verification, pinning, or integrity checks. If the distribution endpoint, network path, or hosting account is compromised, this becomes an immediate arbitrary code execution vector on the local machine.
Content: Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

oo: command not found — install the oo CLI (other platforms: https://cli.oomol.com/install-guide.md):

bash
curl -fsSL https://cli.oomol.com/install.sh | bash # macOS / Linux

powershell

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The description says to use this skill for "ANY Cloudflare Browser Run request," which is an overly broad trigger phrase that can cause the agent to invoke this skill in situations where a narrower or safer tool selection decision should be made. In an agent environment, broad routing language increases the chance of unintended execution paths and can bypass more context-aware handling of user intent.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.