ClawHub
Back to skill

Security audit

Memory Research

Security checks for vulnerabilities and agentic risk

Overview

This skill performs disclosed web research and only stores a Basic Memory note after user approval, though its bare-name and URL triggers are broad.

Install this if you want an agent to research names, URLs, companies, people, technologies, or topics and optionally save structured notes. Be careful with bare names or URLs if you did not intend research, and review any proposed Basic Memory creation or update before approving it.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill activates on very broad implicit inputs such as a bare name or any URL, which can cause unintended invocation when the user did not actually request web research or memory creation. In an agent environment, this can lead to unnecessary external lookups, unexpected data collection, and accidental persistence of information derived from ambiguous prompts, increasing privacy and workflow integrity risks.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.