Security audit

vardoger — Analyze History

Security checks across malware telemetry and agentic risk

Overview

This skill is transparent about its goal, but it reads broad past conversation history and writes derived personalization into global assistant rules, so users should review it carefully before installing.

Install only if you intentionally want an assistant to analyze prior OpenClaw conversations and save derived preferences into global assistant rules. Review the generated personalization before relying on it, avoid running it on histories containing secrets or sensitive personal data, and verify the external vardoger CLI source before granting filesystem access outside the workspace.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (3)

Ssd 3

High

Confidence: 95% confidence
Finding: The skill explicitly directs the assistant to read full conversation history from external session directories and derive outputs from that data. This creates a clear data-exposure pathway because sensitive information from prior conversations can be surfaced, transformed, or reused without granular consent or minimization.

Ssd 3

High

Confidence: 96% confidence
Finding: These steps instruct the assistant to read batch outputs containing conversation data and summarize behavioral signals. Even if the intended output is abstract, the assistant necessarily processes sensitive historical content in natural language, increasing the risk of inadvertent disclosure, retention, or inclusion of private details in summaries.

Ssd 3

High

Confidence: 97% confidence
Finding: The skill instructs the assistant to synthesize findings from historical conversations and persist them into a global rules or personalization file outside the workspace. Persisting derived content extends the lifetime and reach of potentially sensitive historical data, making future unintended disclosure or misuse more likely.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.