Back to skill

Security audit

Mb Init

Security checks for vulnerabilities and agentic risk

Overview

This skill creates a project-local memory-bank documentation folder and includes a git commit step, which is disclosed and purpose-aligned but should be reviewed before use.

Install only if you want an agent to create a memory-bank documentation structure in a project. Before running it, confirm the absolute project root, review the files it plans to create, and treat the git commit step as optional until you have inspected the generated documentation.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 208)May include surrounding context.

md
- [mb-text-workflow](SKILL.md) — For text-based projects

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 209)May include surrounding context.

md
- [mb-text-workflow](SKILL.md) — For text-based projects

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly instructs running git add and git commit, which mutates repository history in addition to creating local documentation files. In an agent context, version-control writes are a higher-risk side effect because they can persist unintended changes, trigger downstream automation, and make rollback harder if performed without an explicit user confirmation step.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill directs creation of directories and files in the target project but does not prominently warn that it will modify the filesystem and may later alter git history. In a normal human-run setup this is expected behavior for an initialization tool, but for an autonomous agent this omission increases the chance of unexpected writes in the wrong project root or repository.

Content

No source excerpt is available for this finding.