Back to skill

Security audit

evrmem

Security checks for vulnerabilities and agentic risk

Overview

This local memory skill is purpose-aligned, but needs review because it tells an agent to automatically install and run unpinned external code while keeping persistent memories under the user's home directory.

Install only if you are comfortable with a local memory database that persists across sessions and with an agent installing external Python packages and model files. Prefer reviewing or pinning the evrmem package and model source, using a virtual environment, and avoiding storage of secrets or untrusted instructions until the skill documents review and deletion controls.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:159
Finding

Automatic Installation and Execution of Unpinned Third-Party Dependencies

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Persistent Context Injection

Medium
Category
Memory Poisoning
Confidence
85% confidence
Finding

The skill explicitly supports storing arbitrary user-provided content into persistent semantic memory (Save this to memory / Remember this information). This creates a persistent prompt/context injection surface where malicious or sensitive content can be stored and later retrieved to influence future model behavior or leak data across tasks.

Content

Scanner excerpt · SKILL.md (reported line 15)May include surrounding context.

md
Use this skill when the user asks to:
- "Search memories" or "Find related memories"
- "Save this to memory"
- "Remember this information"
- "Search my knowledge base"
- "Find past notes about X"

Session Persistence

Medium
Category
Rogue Agent
Confidence
84% confidence
Finding

The configuration defines a persistent storage location under the user's home directory for memory and settings, enabling information to survive across sessions. In an agent context, session persistence increases the chance of unintended retention of sensitive data, cross-task contamination, and later retrieval of attacker-seeded content.

Content

Scanner excerpt · SKILL.md (reported line 114)May include surrounding context.

Configuration

Create ~/.evrmem/config.yaml:

yaml
vector_db:

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructs the agent to run pip install evrmem and evrmem init, which changes the host environment and may download and execute unpinned third-party package code and a large model without explicit user approval. In an agent setting, this is dangerous because it can trigger unauthorized system modifications, supply-chain risk, and unexpected network activity.

Content

No source excerpt is available for this finding.