CMMI认证助手/CMMI-cert-assistant

• Outcome: Pass
• Latest audit: Jun 8, 2026 at 1:58 PM UTC
• Version:
  1.0.0

Overview

This skill is a disclosed CMMI document-assistance tool that reads user-provided project documents and can generate template DOCX outputs, with no evidence of exfiltration, persistence, credential use, or destructive behavior.

Install only if you are comfortable having uploaded project documents analyzed for CMMI mapping. Treat generated documents as templates or drafts rather than certified evidence, review all gap-analysis results manually, and choose output paths carefully to avoid overwriting important files.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (7)

Description-Behavior Mismatch

Medium

• Confidence: 90% confidence
• Finding: The skill metadata promises document conversion from uploaded project documents, but this script only generates a blank DOCX template from static PA configuration. In a certification-assistance context, this mismatch can mislead users into believing uploaded evidence is being analyzed or transformed when it is not, creating integrity and trust risks around compliance workflows.

Description-Behavior Mismatch

Medium

• Confidence: 92% confidence
• Finding: The manifest claims PA matching and gap analysis capabilities, but the code only loads JSON configuration and emits placeholder sections. In a CMMI certification assistant, overstating analytical capabilities is dangerous because teams may rely on generated outputs for appraisal preparation despite no real evidence mapping or gap detection occurring.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The README explicitly states that PA matching and document generation run automatically upon document upload, without manual confirmation in most cases. In a skill that accepts project documents and can generate output files, this broad auto-trigger increases the risk of unintended processing of sensitive content and unexpected file creation, especially if uploads are accidental or malformed.

Missing User Warnings

Medium

• Confidence: 83% confidence
• Finding: The README advertises one-click automatic generation of compliant .docx documents but does not warn users that the skill may create or transform files as part of normal operation. This can lead to unexpected file creation, overwrite risks, or user confusion about where generated artifacts go, which is more concerning in a compliance-focused workflow handling important project evidence.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The README says uploaded project documents are automatically analyzed and used for PA matching, gap analysis, and compliant document generation, but it provides no privacy, retention, or data-handling warning. Because CMMI appraisal materials often include internal process documents, plans, and test artifacts, silent automatic processing increases the risk of exposing confidential business information or creating compliance-related data governance issues.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The skill directs automatic processing of uploaded documents and automatic generation of compliance outputs without confirming user intent or warning about how uploaded content will be used. This can expose sensitive project documents to unintended processing, especially because CMMI artifacts often contain proprietary, contractual, or security-relevant information.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The documented workflow generates and saves DOCX files to user-specified paths but provides no warning about file creation, overwrite risk, or destination effects. In environments with shared storage or broad filesystem access, this can lead to accidental overwrites, placement of sensitive generated artifacts in unsafe locations, or confusion about where data was written.

VirusTotal

65/65 vendors flagged this skill as clean.