Back to skill

Security audit

No Amnesia

Security checks for vulnerabilities and agentic risk

Overview

This is a small documentation-only skill about preserving OpenClaw work context, with no executable code or hidden behavior found.

Before installing, review any actual memory or recovery files that accompany this skill, back up existing OpenClaw memory files, and test recovery on a small task first. The inspected artifact itself is documentation-only and does not perform changes automatically.

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
Vulnerability Patterns
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • 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)

Memory Manipulation

High
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Content

Scanner excerpt · SKILL.md (reported line 47)May include surrounding context.

md
## Recommended test
Before relying on it fully:
1. Create a small task with clear context.
2. Trigger a restart or recovery scenario.
3. Confirm the task context reloads correctly.
4. Adjust the file layout or hooks if needed.

Static analysis

No suspicious patterns detected.