Back to skill

Security audit

mem-load

Security checks for vulnerabilities and agentic risk

Overview

This skill transparently loads local memory-bank context when invoked and does not show hidden execution, network access, writes, or persistence.

Install this only if you want an invoked $mem-load workflow to place recent memory-bank task and session context into the active agent session. Keep credentials, personal data, and unrelated confidential notes out of memory-bank files, and prefer runtimes that keep referenced paths limited to the project memory-bank.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • 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
Findings (1)

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
SKILL.md:17
Finding

Overly Broad Access to Persistent Agent Context and Session Data

Content
View full analysis
Remediation
View remediation
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