Security audit

AI Memory System

Security checks for vulnerabilities and agentic risk

Overview

This skill is purpose-aligned but needs Review because it installs an ongoing nightly AI task that stores conversation-derived facts without clear limits or deletion controls.

Install only if you intentionally want persistent local AI memory. Before setup, confirm the exact cron command, timezone, data scope, where memory files will be stored, how to inspect and remove the cron job, and what categories of information must never be saved.

A.I.G

Vulnerability Patterns

System PersistenceInstalls backdoors, hooks, services, or scheduled tasks that survive the run
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (2)

T06 · System Persistence

Error

Location: SKILL.md:45
Finding: Persistent Nightly Agent Execution Through a Scheduled Task
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Error

Location: SKILL.md:50
Finding: Unbounded Plaintext Retention of Conversation-Derived Personal Information
Content: View full analysis
Remediation: View remediation

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 (3)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The activation phrase "Set up the memory system" is generic enough that it could be triggered during ordinary assistance or discussion about note-taking, causing the agent to perform setup actions unexpectedly. Because the documented behavior includes file creation and scheduled task installation, an accidental trigger can lead to unauthorized persistence and state changes on the user's system.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill's setup description leads to filesystem changes and installs a recurring cron job, but the user-facing description does not prominently warn about these side effects before activation. This weakens informed consent and increases the chance that a user enables persistent automation without understanding that it will continue running and modifying memory files over time.
Content: No source excerpt is available for this finding.

Ssd 3

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill instructs the agent to persistently log conversations, user preferences, decisions, and extracted facts into local memory files and to summarize them automatically on a schedule. This creates privacy and data-retention risk because sensitive personal or business information may be stored long-term without clear minimization, consent boundaries, review controls, or exclusion rules.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.