Security audit

Word2md

Security checks for vulnerabilities and agentic risk

Overview

This skill is a legitimate document-to-Markdown helper, but it may send office documents to an external cloud service in situations where the user only asked to read or summarize them.

Install only if you are comfortable sending selected DOCX, PPTX, XLS, or XLSX files or document URLs to MinerU's cloud API. Avoid using it for confidential, regulated, or enterprise documents unless your organization approves that external processing, and prefer confirming each upload before conversion.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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 (2)

T01 · Skill Instruction Hijacking

Warning

Location: SKILL.md:31
Finding: Skill-Level Language Directive Overrides Session Behavior
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Warning

Location: SKILL.md:5
Finding: Unpinned Third-Party CLI Dependencies Permit Unreviewed Supply-Chain Changes
Content: View full analysis
Remediation: View remediation

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 (1)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill's activation guidance is broad enough to match generic requests to read, extract, summarize, or analyze office documents, which can cause the agent to invoke this skill in situations where users may not expect cloud processing. Because the skill supports direct URL input and explicitly uploads documents to a third-party service without authentication, over-triggering increases the chance of unintended data disclosure or use on sensitive files.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.