use-just-bash-for-scripts

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructions for using 'just-bash' from Vercel Labs, a utility designed to run shell scripts in a sandboxed environment with an overlay filesystem. This is a defensive security practice intended to mitigate risks from executing untrusted code.
  • [EXTERNAL_DOWNLOADS]: The skill mentions checking for and potentially installing the 'just-bash' utility. This tool is associated with Vercel, a well-known service provider, and is used here specifically for its sandboxing capabilities.
  • [SAFE]: This skill addresses the attack surface for Indirect Prompt Injection by providing a sandboxed execution environment.
  • Ingestion points: Shell scripts, command sequences, and untrusted snippets provided by users or generated by the agent (SKILL.md).
  • Boundary markers: The skill functions as a procedural boundary by directing execution into the 'just-bash' sandbox.
  • Capability inventory: Shell command execution via the 'just-bash' CLI.
  • Sanitization: Relies on the 'just-bash' overlay filesystem (writes stay in memory) and default disabled network access to prevent host side effects or data exfiltration.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 11:20 AM
Security Audit — agent-trust-hub — use-just-bash-for-scripts