Security audit

Neural Memory Enhanced

Security checks for vulnerabilities and agentic risk

Overview

This memory skill appears purpose-built rather than malicious, but it needs review because it can automatically store conversation details persistently and installs unpinned external code that configures the agent.

Review this before installing if your conversations may contain secrets, personal data, regulated information, or client/business details. Prefer an isolated environment, pin and verify the package version if possible, inspect what nmem init changes, and use the memory tools only with data you are comfortable retaining locally across sessions.

A.I.G

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:27
Finding: Unpinned Third-Party Package Installation and Execution
Content: View full analysis
Remediation: View remediation
``` 2. Require package integrity verification using hashes: ```bash python3 -m pip install --require-hashes -r requirements.txt ``` Maintain a reviewed requirements or lock file containing exact versions and SHA-256 hashes for the package and all transitive dependencies. 3. Link the Skill release to the exact source commit and package artifact that were audited. Prefer reproducible builds and signed release artifacts where available. 4. Install the package in an isolated virtual environment rather than the user's global Python environment: ```bash python3 -m venv .venv .venv/bin/python -m pip install --require-hashes -r requirements.txt ``` 5. Document all filesystem and configuration changes made by `nmem init`. Require explicit user confirmation before modifying `~/.openclaw/mcp.json`, project configuration, or existing memory databases. 6. Provide a non-mutating inspection or dry-run mode for initialization so users can review proposed configuration changes before applying them. 7. Review and constrain optional network-enabled components, including embedding providers, before processing sensitive conversation data. 8. Correct or clarify the installation metadata where the installer entry uses `"kind":"node"` while directing users to install a Python package with `pip`, reducing ambiguity in automated installation behavior. ]]>

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 (2)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill prominently advertises remembering facts, decisions, errors, and context across sessions, but does not provide an upfront warning that conversation-derived information may be stored persistently. This creates a meaningful privacy and consent risk because users may disclose sensitive information without realizing it will be retained locally and later surfaced in future sessions.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill instructs proactive use in very broad situations such as starting a new task, after errors, and whenever past context might help. In a memory skill that persists data across sessions, this can cause over-collection and unsolicited retrieval of sensitive user or conversation data without a clear necessity or user awareness.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.