opencode-cli

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands through the opencode CLI and the bash tool. It provides a structured workflow for session management and background process monitoring using the process tool (e.g., process action:poll).
  • [INDIRECT_PROMPT_INJECTION]: The skill processes arbitrary user prompts through the opencode run command, which constitutes a vulnerability surface where malicious content in project files or user input could influence the agent's actions.
  • Ingestion points: User prompts are passed as arguments to the opencode run command in SKILL.md and references/tips-guide.md.
  • Boundary markers: The CLI uses a -- separator for the prompt, but there are no specific prompt delimiters or instructions to ignore embedded commands within the input data.
  • Capability inventory: The skill has access to powerful tools including bash, read, write, edit, and background process management.
  • Sanitization: No explicit sanitization or validation of the input prompt is described in the skill's instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 11:32 PM
Security Audit — agent-trust-hub — opencode-cli