Security audit

Docx Editing

Security checks for vulnerabilities and agentic risk

Overview

This skill is a DOCX editing helper with disclosed local file and npm setup risks, and no evidence of hidden exfiltration, persistence, or destructive behavior.

Install only if you are comfortable running the Safe-DOCX npm MCP server with access to DOCX files under your home directory and temp folders. Prefer the pinned or vendored install path, review the package/source before use in sensitive environments, and keep edits directed at explicit input documents.

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:52
Finding: Execution of an Externally Retrieved and Unaudited npm Package
Content: View full analysis
npm ci npm run build npm link packages/safe-docx ``` `SKILL.md:111-122`: ```json { "mcpServers": { "safe-docx": { "command": "npx", "args": ["-y", "@usejunior/safe-docx@0.9.0"] } } } ``` `CONNECTORS.md:23-31`: ```json { "mcpServers": { "safe-docx": { "command": "npx", "args": ["-y", "@usejunior/safe-docx@0.9.0"] } } } ``` `CONNECTORS.md:76-88`: ```bash git clone https://github.com/UseJu ...[truncated 3956 chars]
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
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

Findings (2)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The skill description includes broad trigger phrases such as 'change the contract,' 'read this Word file,' and 'mark up the agreement,' which are common everyday requests and may cause the skill to be invoked in situations the user did not explicitly intend. Unintended invocation matters here because the skill can read and modify local .docx files, so an overly eager match could expose sensitive documents or perform edits in the wrong workflow.
Content: No source excerpt is available for this finding.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 96% confidence
Finding: The skill recommends launching the MCP server with an unpinned package reference (npx -y @usejunior/safe-docx), which allows whatever version is current in the npm registry or cache to be executed. That creates a supply-chain risk: a compromised publisher account, malicious new release, dependency compromise, or unexpected breaking update could result in execution of unreviewed code on the host machine.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.