ClawHub
Back to skill

Security audit

Agentmemory Rest Api

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed reference for using a localhost memory REST API and does not include executable code, installation steps, persistence, or hidden behavior.

Install only if you intend agents to use a local agentmemory REST service. Enable AGENTMEMORY_SECRET for shared or sensitive environments, keep the service bound to localhost, and avoid storing secrets or private data unless you understand who can access the memory server.

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
  • 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
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly documents that the localhost REST API is unauthenticated by default and provides write/read examples against a memory service without any warning about sensitivity, local privilege boundaries, or the risks of exposing the service beyond localhost. Even when bound to localhost, other local processes, browser-based localhost access paths, or misconfigurations can abuse the API to read or modify memory data, making this an insecure-by-default interface description.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 13)May include surrounding context.

bash
# liveness
curl -fsS http://localhost:3111/agentmemory/livez

# save
curl -X POST http://localhost:3111/agentmemory/remember \

Static analysis

No suspicious patterns detected.