ClawHub

Pattern Recognition

Security checks across malware telemetry and agentic risk

Overview

The skill appears purpose-aligned, but it can recursively read agent memory and logs and persist extracted examples without clear redaction, opt-in, or access boundaries.

Install only if you are comfortable with the skill processing local OpenClaw memory, logs, and metrics. Review those directories for secrets or sensitive user/project content first, and prefer running it on sample or sanitized data until the skill adds clearer source controls, redaction, and retention behavior.

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 (2)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill is designed to automatically learn from operations, errors, resources, backlog files, scripts, and task memory, but it provides no access boundaries, data minimization rules, or warnings about potentially sensitive content in those sources. In an agent environment, this can cause broad ingestion of logs, workflow history, and stored artifacts that may include secrets, internal context, or sensitive operational metadata, increasing the risk of unintended disclosure and unsafe template propagation.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The script recursively reads operational memory, logs, and metrics from the workspace and extracts command, workflow, and error content without any access controls, minimization, consent, or notice. In this skill context, those sources can contain sensitive commands, paths, filenames, error text, and operational history, so indiscriminate collection creates a meaningful privacy and data-handling risk even though there is no obvious exfiltration in this file.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal