ClawHub
Back to skill

Security audit

ClawCache Free - LLM Cost Tracking & Caching

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a legitimate local LLM cost tracker/cache, but its installation instructions are inconsistent enough that users could install the wrong Python package.

Review the package before installing, and prefer the package name that matches the project metadata (`clawcache-free`) rather than conflicting examples. Use it only where local retention of prompts, responses, token metadata, and cost logs is acceptable, and set `CLAWCACHE_HOME` to a protected location or avoid using it with secrets or regulated data.

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
93% confidence
Finding
The README promotes automatic logging of every LLM API call and automatic caching of responses, but it does not clearly warn that prompts and responses may be persisted locally in SQLite/log files and can contain secrets, personal data, proprietary code, or regulated information. This can lead users to enable the feature in sensitive environments without understanding the privacy and data-retention implications, increasing the risk of unintended local disclosure.

Missing User Warnings

Medium
Confidence
87% confidence
Finding
The skill prominently markets automatic logging and caching of LLM calls, but the documentation does not clearly disclose that prompts, responses, and related metadata may be persisted locally in SQLite/log files. In a developer tool handling arbitrary user prompts, this can lead to inadvertent storage of secrets, personal data, or proprietary code, increasing privacy and data exposure risk on shared or compromised systems.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal