Back to skill

Security audit

M-Flow Memory

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent memory-management skill, but it stores and indexes user-provided content with unclear retention/control and imports an external local M-Flow package through an unsafe path mechanism.

Review this skill before installing if you may handle private or sensitive conversations. Use it only when you intentionally want content persisted into M-Flow memory, confirm where M-Flow stores data, how to delete it, and who or what agents can search it. Also ensure the sibling m_flow dependency path is trusted and not writable by untrusted users.

Vulnerability Patterns
  • Tool Hijacking and SpoofingModifies or replaces tools so legitimate-looking calls execute attacker logic
  • 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
Findings (2)

T07 · Tool Hijacking and Spoofing

Warning
Location
scripts/__init__.py:10
Finding

Unvalidated Python Module Search Path Enables Local Module Hijacking

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Note
Location
SKILL.md:57
Finding

Dependency Installation Instructions Do Not Enforce Package Integrity

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 46)May include surrounding context.

HF_HUB_OFFLINE=1

text

### .env 配置 (m_flow/.env)

LLM_PROVIDER="ollama" LLM_MODEL="ollama/qwen2.5:14b-instruct-q8_0"

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

Most of the operational instructions, activation conditions, and usage guidance are presented only in Chinese, which effectively forces a specific language on users. The file does not indicate that this is a region-specific skill or offer an alternative language option.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation criteria are broad enough that the skill could trigger on ordinary user requests involving search, knowledge, or memory, causing persistence or retrieval actions without clear user intent. In a memory-management skill, ambiguous activation increases the chance of over-collection and unintended processing of conversation content.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill demonstrates adding, indexing, and searching memory content but does not warn that user conversations or knowledge points may be stored and processed persistently. This creates a privacy and consent risk because users may disclose sensitive information without realizing it will enter a long-lived memory system.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The file’s natural-language strings and comments indicate the skill is explicitly framed as a Chinese-language test script, with no indication that language selection is optional. Under the policy, forcing a specific language without user opt-in is a locale/language policy violation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The documentation includes endpoint and API-key style environment variables in a .env configuration example without guidance on protecting credentials or avoiding accidental disclosure. Even though the sample uses local Ollama and a placeholder key, normalizing plaintext secret handling can lead operators to place real credentials in insecure files or commit them to source control.

Content

No source excerpt is available for this finding.