Index of every page on this site: llms.txt

/

/rivet-sandbox-agent

@3d287ca official

by Rivetrivet-dev/skills41 stars

10

Run it yourself

Sandbox Agent: Run coding agents in sandboxes. Control them over HTTP..

1 file
21.3 KB
Updated 2 weeks ago
GitHub
No alerts

Use this Skill: https://skilld.dev/gh/rivet-dev/skills/rivet-sandbox-agent

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

21.3 KB raw

≈23 tokens for metadata: the name and description. ≈5.4k when used: this file.

Description uses 1.2% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈93 characters, or 1.2%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Documentation

Source: SKILL.md on GitHub

Skill behaviors

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

Third-party checks

No alerts9d3 checks · Risk SAFE

Gen Agent Trust Hub9d
This skill provides documentation and access to a high-capability 'Sandbox Agent' designed for coding automation. The documented APIs include powerful system controls such as command execution, file system manipulation, and desktop monitoring (screenshots, clipboard access). While intended for use in isolated environments, the combination of these capabilities with agents that process external data creates a significant surface for indirect prompt injection and potential data exposure.
Socket9d
No alerts
Snyk9d
Risk: LOW · No issues

Provenance

Signed by skilld at 3d287ca. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 2 weeks ago