OpenClaw Hook Examples

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only skill with OpenClaw hook examples; it does not install or run code, but one logging example should be treated carefully before reuse.

Installing this skill should only add reference material. Before turning the examples into a real plugin, avoid logging raw tool arguments, outputs, or session identifiers; use allowlisted fields, redaction, restricted log access, and clear retention rules.

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 (1)

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The example audit hook records raw tool parameters and a session identifier, which can expose secrets, personal data, or other sensitive operational context if copied into real deployments. Even though this is documentation/example content rather than active code, examples strongly influence implementation patterns, and there is no warning, redaction, or minimization guidance to reduce leakage risk.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal