Back to skill

Security audit

Memfy

Security checks for vulnerabilities and agentic risk

Overview

Memfy is a small memory-saving skill whose durable file writes are disclosed, purpose-aligned, and constrained to user-requested non-secret context.

Install this only if you want the agent to append durable notes to a local memory file when you ask it to remember things. Avoid asking it to save secrets or sensitive personal data, and review the chosen memory file periodically because entries persist across sessions.

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
  • 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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is designed to save durable memory, but the manifest does not provide a user-facing warning or confirmation mechanism before persistence occurs. Because stored memory may include sensitive personal details or inaccurate inferred facts, silent or low-visibility saving can lead to privacy harm, consent issues, and long-lived data retention problems.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest enables implicit invocation and uses a broad default prompt to save durable details from conversation, which can overlap with ordinary user discussion about remembering things for later. This creates a real risk of unintended activation and memory capture without sufficiently explicit, contemporaneous user intent, especially because the skill handles persistence across sessions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.