Security audit

NBJ OB1 Agent Memory for OpenClaw

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed memory-workflow guide that asks agents to recall and write compact project context, with safeguards against storing secrets or silently promoting unreviewed memory.

Install this only if you want OpenClaw agents to use OB1/OpenBrain persistent memory across tasks. Before using it on sensitive projects, confirm the OB1 service enforces project and tenant boundaries, protects provenance/use-policy labels, and lets you review, revoke, or audit stored memories.

A.I.G

Vulnerability Patterns

Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
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

Findings (1)

T02 · Agent Memory Poisoning

Warning

Location: SKILL.md:28
Finding: Persistent Agent Memory Can Influence Future Sessions
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Static analysis

No suspicious patterns detected.