Back to directory

Sandboxing Untrusted Input

Agent skill
1 skill

Bounds blast radius when a session ingests untrusted input (web pages, GitHub issues, scraped content, MCP output) via the Agents Rule of Two plus filesystem/egress deny rules. Use whenever the agent processes content from an unknown party.

Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI

Supported by the Atlas install prompt. Skill-specific requirements vary.

Skill stats

Skills1CategoryGeneralStars0

About this skill

Bounds blast radius when a session ingests untrusted input (web pages, GitHub issues, scraped content, MCP output) via the Agents Rule of Two plus filesystem/egress deny rules. Use whenever the agent processes content from an unknown party.

Quick start

  1. Copy the install prompt. Use the green button above this README.
  2. Send it to your agent. Paste it into your coding agent’s chat and send.
  3. Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.
Review, license & listing details
Review the source before using this skill

This is an imported listing. We haven’t certified its safety, license, or compatibility. Skills may include executable scripts.

Automated security scan: Partial

Only SKILL.md was scanned. Supporting files and scripts were not checked. No safety grade has been assigned.

0 potential findings · Scanned 11/4/2026 · Scanner 0.2.1

Content SHA-256: 728ca592879fc3644ea33f0bccd13c6ca568e8796eb2bd75911b92f2f4a5eb2f

About scan coverage and limitations

About this listing

Category
General
Reported license
Not specified
Listing language (estimated)
English
Review status
Not individually reviewed
Agent compatibility
Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.
Sandboxing Untrusted Input | Agent Skills Atlas