skills/different-ai/openwork/daytona/Gen Agent Trust Hub

daytona

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the Daytona CLI using the Homebrew package manager (brew install daytonaio/cli/daytona) from the official vendor repository.
  • [COMMAND_EXECUTION]: The skill utilizes shell commands to manage development sandboxes, including the execution of local repository scripts (e.g., .devcontainer/test-on-daytona.sh) and Daytona CLI operations (daytona login, daytona preview-url, daytona delete).
  • [DATA_EXPOSURE]: The skill provides instructions for managing environment variables and secrets through a helper script (setup-daytona-secrets-volume.sh) that handles .env files. This aligns with standard development practices for local secret management.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest user-supplied parameters into shell commands.
  • Ingestion points: Placeholders such as <ref>, <slug>, <local-env>, and <sandbox> in SKILL.md.
  • Boundary markers: None present.
  • Capability inventory: Shell command execution via bash and the daytona CLI.
  • Sanitization: None present in the instructional text.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 03:07 AM