ClawHub
Back to skill

Security audit

RecallBase

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local recall helper that clearly discloses it will query local AI conversation history and keeps that behavior aligned with its purpose.

Install only if you are comfortable letting the agent query your local AI conversation history. Keep requests specific, and require explicit approval before running imports, package installation, or browser native-host setup.

SkillSpector

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 (1)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The default prompt uses an extremely broad, everyday phrase ('summarize what I worked on today') that could cause the skill to activate in normal conversation without strong user intent or scope checks. Because this skill accesses local AI conversation history, accidental invocation could expose sensitive prior chats, coding context, or decision history beyond what the user explicitly meant to retrieve.

Static analysis

No suspicious patterns detected.