ClawHub
Back to skill

Security audit

Foxcode Openclaw

Security checks across malware telemetry and agentic risk

Overview

The skill mostly does what it says, but it handles API tokens and rewrites OpenClaw configuration in ways users should review carefully before installing.

Install only if you are comfortable giving the skill your Foxcode API token and allowing it to change OpenClaw configuration files. Back up ~/.openclaw/openclaw.json and auth-profiles.json first, avoid putting real tokens in shell startup files or shared configs, and do not run validate_config.py on configs with untrusted custom baseUrl values.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill instructs users to enter a Foxcode API token and notes that it will be saved to a local auth file, but it does not clearly emphasize that this is a sensitive secret requiring protected storage, limited permissions, and careful handling. In a skill that edits auth material and encourages beginners to use it, insufficient credential-safety guidance materially increases the risk of accidental exposure through backups, file sharing, weak permissions, or misconfigured systems.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The document includes authentication and configuration examples that place an API key directly in headers, environment variables, and especially a JSON config snippet without any accompanying warning not to hardcode, share, or commit secrets. In a beginner-focused setup guide, users are more likely to copy these examples verbatim into files or repositories, increasing the risk of credential exposure and unauthorized API use.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The documentation instructs users to append a live API token directly into shell startup files, which makes the secret persist in plaintext on disk and easy to leak through backups, dotfile syncing, shoulder-surfing, or accidental sharing. While this is common convenience guidance, it omits warnings and safer alternatives for secret storage, so it creates avoidable credential exposure risk.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The validator performs a live network check and includes the configured API token in an Authorization header to whatever baseUrl is present in the config, including custom endpoints. In a validation tool this can unintentionally disclose credentials to an attacker-controlled URL or surprise users who expected only local syntax checking, especially because there is no explicit opt-in warning before the request is made.

Session Persistence

Medium
Category
Rogue Agent
Content
# macOS/Linux
export FOXCODE_API_TOKEN="sk-foxcode-your-token"

# Add to ~/.zshrc or ~/.bashrc for persistence
echo 'export FOXCODE_API_TOKEN="sk-foxcode-your-token"' >> ~/.zshrc
```
Confidence
94% confidence
Finding
Add to ~/.zshrc

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.