Free Ride - Unlimited free AI

• Outcome: Review
• Latest audit: Jul 10, 2026 · 3:46 AM UTC
• Version: 1.0.11

Overview

FreeRide matches its stated purpose, but it deserves Review because it can persistently change OpenClaw model routing and run an optional background watcher that keeps probing and rewriting configuration.

Install only if you want FreeRide to manage OpenClaw's default and fallback model routing. Back up ~/.openclaw/openclaw.json first, keep the OpenRouter API key private, and run freeride-watcher only if you knowingly want a background process that may continue making OpenRouter requests and changing model settings until stopped.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Rogue Agent: Self-Modification, Session Persistence
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection

Findings (8)

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 94% confidence
• Finding: The skill's description understates materially important behaviors: live API probing, autonomous rotation logic, a persistent background watcher, and ongoing state/history writes. That mismatch can cause users or orchestrators to grant execution under the assumption it only updates configuration, when it also performs continuous network activity and autonomous reconfiguration with a secret-bearing API key.

Missing User Warnings

Medium

• Confidence: 86% confidence
• Finding: The README instructs users to persistently modify OpenClaw configuration and later introduces a long-running watcher/daemon, but it does not clearly warn that these changes are durable, may alter routing behavior across sessions, and may keep running in the background until manually stopped. In a skill that manages model selection and API keys, lack of explicit safety guidance can lead to unintended persistent behavior, surprise outages, or continued use of external services after the user believes the change is temporary.

Vague Triggers

Medium

• Confidence: 81% confidence
• Finding: The activation text uses broad trigger phrases like 'free AI,' 'model switching,' 'rate limits,' and 'reduce AI costs,' which can match many normal conversations and cause the skill to be invoked unexpectedly. Because this skill can rewrite config and restart services, over-broad activation increases the chance of unintended system changes without sufficiently specific user intent.

Missing User Warnings

Medium

• Confidence: 86% confidence
• Finding: The skill overwrites the user's active OpenClaw configuration file in place without confirmation, backup, file locking, or atomic write handling. This can unintentionally disrupt the user's model/provider setup or corrupt configuration if the process is interrupted, especially because the tool changes primary and fallback routing automatically.

Session Persistence

Medium

• Category: Rogue Agent

Content

freeride-watcher

# Background, persistent across logout
nohup freeride-watcher > ~/.openclaw/freeride-watcher.log 2>&1 &

# One-off check (no loop)
freeride-watcher --once

• Confidence: 88% confidence
• Finding: nohup

Session Persistence

Medium

• Category: Rogue Agent

Content

freeride-watcher

# Persistent background
nohup freeride-watcher > ~/.openclaw/freeride-watcher.log 2>&1 &

# One-shot check (no loop)
freeride-watcher --once

• Confidence: 92% confidence
• Finding: nohup

Unpinned Dependencies

Low

• Category: Supply Chain

Content

requests>=2.31.0

• Confidence: 86% confidence
• Finding: requests>=2.31.0

Known Vulnerable Dependency: requests==2.31.0 — 5 advisory(ies): CVE-2024-47081 (Requests vulnerable to .netrc credentials leak via malicious URLs); CVE-2024-35195 (Requests `Session` object does not verify requests after making first request wi); CVE-2026-25645 (Requests has Insecure Temp File Reuse in its extract_zipped_paths() utility func) +2 more

Medium

• Category: Supply Chain
• Confidence: 92% confidence
• Finding: requests==2.31.0

VirusTotal

65/65 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.