ClawHub
Back to skill

Security audit

agentic-ledger

Security checks across malware telemetry and agentic risk

Overview

The skill is a local cost ledger that clearly discloses its proxy setup and local prompt/response logging, though users should understand the privacy implications before enabling it.

Install only if you are comfortable routing OpenClaw model calls through a local proxy that records full prompts and responses on your machine. Review where the ledger stores data, how to delete or secure it, and avoid enabling it for highly sensitive work unless local transcript retention is acceptable.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger phrases are broad enough to activate on common requests about usage, spend, or what the agent has been doing, which can cause the skill to run in many contexts. Because this skill performs host-side network reads and exposes operational history, over-triggering increases the chance of unnecessary access to sensitive logs or confusing, privacy-impacting behavior.

Missing User Warnings

High
Confidence
97% confidence
Finding
The skill explicitly states that every prompt and response is recorded locally, but it does not present a clear privacy warning at the point of use or require explicit user consent before enabling or querying that logging. Prompts and responses can contain secrets, personal data, proprietary code, or regulated information, so comprehensive transcript capture materially raises confidentiality and compliance risk even if data stays on the same machine.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.