Skip to main content

TH16802

Detected presence of AI assistant extensions that execute unusual system commands.

priorityCI/CD statusseverityeffortSAFE levelSAFE assessment
failhighhigh1tampering: fail
Reason: dangerous AI extensions

About the issue​

AI assistant extensions are commonly used by software developers to extend the functionality of AI coding assistants, agentic development tools, and other AI-powered developer tools. Extensions are typically distributed through public marketplaces as packages that bundle skill instruction files with supporting resources. Skill instruction files describe specialized capabilities that the AI assistant can invoke, such as guidance for handling specific file formats, performing domain-specific tasks, or interacting with particular services. The AI assistant loads instructions from these files into its context and follows them when relevant user requests or workflow events occur. These instructions are written by extension authors to guide the AI assistant toward the intended capability, or to provide additional context for nominal extension use. However, AI assistant extensions are commonly abused by threat actors to influence the AI assistant into performing arbitrary actions within the development environment. It was detected that the skill instruction files could direct the AI assistant to execute unusual operating system commands. Unusual commands resemble common threat actor tactics, such as destructive file deletion, elevation of privileges, or tampering with security settings. Unusual skill instruction files often contain indirect phrasing, misleading context, or other prompt injection techniques.

How to resolve the issue​

  • Investigate reported detections.
  • Consult Mitre ATT&CK documentation: T1176 - Software Extensions.
  • If the AI assistant extension intent does not relate to the reported behavior, investigate your development environment for software supply chain compromise.
  • You should stop using the AI assistant extension until the investigation is completed, or until the issue is risk accepted.
  • Consider replacing the AI assistant extension with an alternative.

Incidence statistics​

ReversingLabs periodically collects and analyzes the contents of popular software package repositories for threat research purposes. Analysis results are used to calculate incidence statistics for issues (policy violations) that Spectra Assure can detect in software packages.

This section is updated when new data becomes available.

Total amount of packages analyzed

  • Linux: 562K
  • NPM: 5.12M
  • Nuget: 735K
  • PS Gallery: 17K
  • PyPi: 838K
  • RubyGems: 203K
  • VS Code: 113K
  • Windows: 3.7K

Total detections per repository

For every repository, the chart shows the number of packages that triggered the software assurance policy. In other words, it shows how many packages in each package repository were found to have the specific issue described on this page. This information helps you understand how common the issue is across different software communities.

If a repository is absent from the chart, that means none of the packages in that repository triggered this policy during analysis, or the policy was not used during analysis.

Distribution of total detections by project popularity

For every repository, the chart shows how many of the total detections belong to the Top 100 (1-100), Top 1000 (101-1000) and Top 10 000 (1001-10 000) most downloaded projects. This information helps you understand the impact of the issue within each community, making it clearer when the issue affects the most popular projects.

If the chart shows zero values for all of the top project groups, that means all detections were in unranked projects (lower than 10 000 on the list of most downloaded projects).