Openclaw Version Bug Hunter

Security checks across malware telemetry and agentic risk

Overview

This skill is a read-only OpenClaw version bug-report lookup helper that uses GitHub CLI, with credential and network use mostly aligned to its stated purpose.

Install only if you are comfortable with the agent running a local Bash script that sends version search terms to GitHub using your gh login. Check gh auth status first, install jq if needed, and ask before letting the agent inspect local OpenClaw configuration.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The skill encourages broad natural-language requests like checking versions, latest stability, or upgrade pitfalls, and says the agent will 'automatically run the script' without clearly constraining when external GitHub queries will occur. This can cause users to trigger networked actions and repository searches implicitly, increasing the chance of unintended data access or surprise execution in response to ordinary language.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill instructs users to install and authenticate the GitHub CLI but does not clearly disclose that authenticated use will send network requests to GitHub and operate with the user's GitHub account context. In an agent setting, this can surprise users and create privacy or account-scope risks, especially if issue queries, comments, or future command extensions are performed with stored credentials.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal