Skip to content

SECURITY.md

Latest commit

 

History

History
89 lines (70 loc) · 4.41 KB

SECURITY.md

File metadata and controls

89 lines (70 loc) · 4.41 KB
Raw

Security Policy

This document should guide you about understanding the security concept behind offsidepi and also where the boundaries are.

In general offsidepi is a coding agent that runs locally within the security boundary of the user that is running it. It's the responsibiltiy of the user to monitor its operations or to contain it within a container, virtual machine or other Sandbox solution.

offsidepi treats the local user account and files writable by that account as inside the same trust boundary as the offsidepi process itself. If an attacker can modify files under the user's home directory, workspace, shell startup files, environment, or offsidepi configuration, they can generally influence offsidepi or other local developer tools. Reports that depend on such prior local write access are not security vulnerabilities unless they demonstrate how offsidepi grants that write access or crosses an operating-system privilege boundary.

offsidepi relies on users installing trustworthy extensions and loading trustworthy skills and only to use offsidepi within trusted repositories. This is because files like AGENTS.md or instructions in comments can be used to prompt inject the coding agent trivially and this cannot be protected against.

Reporting a Vulnerability

If you believe you found a security vulnerability in offsidepi or another package in this repository, please report it privately by:

  • Opening a private report through GitHub Security Advisories for this repository

If the issue also affects the upstream pi project offsidepi is forked from, please additionally report it upstream by emailing security@earendil.com or using upstream's GitHub Security Advisories.

Please include:

  • A description of the issue and its impact
  • Steps to reproduce, proof of concept, or relevant logs
  • Affected package, version, commit, or configuration
  • Any known mitigations

Do not open a public issue for security-sensitive reports. We will review reports and coordinate disclosure as appropriate.

Scope

Security issues in the distributed packages, command-line tools, APIs, and repository code are in scope.

Out Of Scope

  • Local code execution or sandboxing behavior (the offsidepi coding agent intentionally does not have a sandbox)
  • Behavior of offsidepi extensions or skills installed by the user
  • Risks from working in untrusted repositories
  • Risks from installing untrusted extensions, skills, packages, or tools
  • Isuses caused by non trustworthy MITM proxies
  • Public internet exposure of a offsidepi installation
  • Prompt injection attacks
  • Exposed secrets that are third-party/user-controlled credentials
  • Reports requiring the ability to create, modify, delete, or replace files, directories, symlinks, environment variables, shell configuration, or other user-controlled local state on the target machine. This includes ~/.offsidepi, ~/.offsidepi/agent/models.json, workspace files, AGENTS.md, skills, extensions, extension configuration, dotfiles, and files synchronized through NFS, roaming profiles, or dotfile managers, unless the report shows how offsidepi itself grants that access.
  • Issues caused by intentionally weakened user configuration.
  • Resource/DOS claims that require trusted local input/config against the offsidepi coding agent.
  • Reports about malicious model output.
  • User-approved or user-initiated local actions presented as vulnerabilities.

Notes for Reporters

The most useful reports show a current, reproducible security boundary bypass with demonstrated impact. Reports that only show expected local-agent behavior, prompt injection, or a malicious trusted extension/skill are not security vulnerabilities under this model.

For example, a report showing that malicious contents written to a trusted offsidepi configuration file cause offsidepi to execute commands, load attacker-controlled tools, send credentials to an attacker-controlled endpoint, or otherwise change behavior is out of scope.

When possible, include the exact affected path, package version or commit SHA, configuration, and a proof of concept against the latest release or latest main. For dependency reports, include evidence that the shipped dependency is affected and that the issue is reachable through offsidepi. For exposed-secret reports, include evidence that the credential is owned by this project or grants access to infrastructure or services operated by this project.