Continue CLI
Continue's headless CLI agent that runs the same hub assistants/blocks (rules, MCP, prompts) outside an IDE.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for Continue CLI, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
The Continue CLI runs Continue assistants headlessly — driving the same block-based config (rules, MCP servers, prompts, models) in terminals, scripts, and CI, including a GitHub-Actions PR-review bot pattern. Security surface: executes MCP tools and applies rules autonomously in CI/terminal contexts, so bundled MCP servers get shell/tool access.
Key features and capabilities
- Headless agent runtime
- Runs hub rules/MCP/prompts in CI
- PR-review bot via GitHub Actions
Use cases
- Automated PR review in CI
- Terminal/scripted Continue agent runs