oh-my-opencode-update

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • REMOTE_CODE_EXECUTION (HIGH): The skill documentation recommends installing the 'bun' runtime through 'curl -fsSL https://bun.sh/install | bash', a high-risk pattern allowing arbitrary code execution from a third-party source.
  • EXTERNAL_DOWNLOADS (MEDIUM): The skill fetches and executes the 'oh-my-opencode' package from public registries using 'bunx' and 'npm', introducing risks associated with unverified external dependencies.
  • COMMAND_EXECUTION (LOW): The skill performs maintenance tasks including file backups, permission changes, and directory deletions, which grant the agent broad control over the local file system.
  • PROMPT_INJECTION (LOW): Parameters such as '--claude' and '--gemini' are interpolated into shell commands without sanitization, creating a surface for indirect prompt injection. Ingestion points: CLI arguments; Boundary markers: absent; Capability inventory: subprocess execution of npm/bun; Sanitization: absent.
Recommendations
  • HIGH: Downloads and executes remote code from: https://bun.sh/install - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 17, 2026, 06:15 PM