ClawHub
Back to skill

Security audit

Memory Handoff

Security checks for vulnerabilities and agentic risk

Overview

This skill only guides the agent to write short, reviewable memory handoff notes in the repository, with no hidden execution or external data flow.

Installers should understand that this skill may cause the agent to create repo-local memory handoff notes containing durable facts, preferences, setup details, or security findings from a session. Review those files before ingesting them into any long-lived memory system, especially if they mention sensitive project context.

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 description says to use the skill at the end of 'any session that discovered durable knowledge' and also on phrases like 'hand off' or 'write a handoff'. This combines a very broad activation condition with trigger phrases that are common in ordinary collaboration, without negative examples or clearer boundaries for when the skill should not activate.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.