ClawHub
Back to skill

Security audit

Lore

Security checks across malware telemetry and agentic risk

Overview

Lore is a knowledge-base skill whose persistence behavior matches its stated purpose, but users should be mindful about what they allow it to store.

Install only if you want a persistent knowledge repository. Avoid ingesting secrets, credentials, regulated data, or private third-party content unless you are comfortable retaining it there, and confirm how to delete or scope stored material before using it for sensitive work.

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
91% confidence
Finding
The skill explicitly directs the agent to ingest user-shared content and externally fetched material into a persistent knowledge repository, but it provides no requirement for user consent, data minimization, sensitivity screening, or retention controls. This creates a real privacy and data-governance risk because sensitive information from conversations, Slack, email, Notion, or other systems could be stored long-term and later surfaced beyond the original context.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.