The safeguards map / 3.2 Agent harnesses
Cursor
Drafted with AI
Drafted with AI from the cited sources under the direction of UnGovr staff. UnGovr holds editorial responsibility for this page. How this site is made
An AI code editor whose agent has run modes that decide when it asks for approval, a sandbox for terminal commands, and hooks that can block agent actions.
Where it sits
3.2 Agent harnesses (primary): Applies a run mode to the agent's shell, Model Context Protocol (MCP) and fetch calls, with an allowlist, a classifier review or approval prompts, and runs hooks that can block agent actions.
Run Modes control how the Cursor agent runs tool calls, and when Cursor interrupts you for approval.
captured
The sandbox runs terminal commands in a restricted environment that blocks unauthorized file access and network activity.
captured
Hooks let you observe, control, and extend the agent loop using custom scripts.
captured
Facts
- Concern
- safetysecurity
- Names the law
- no
- Subject
- agent
- Used by
- those who run it
- Runs
- at runtimein the IDE
- Policy comes from
- owner-entered settings
- Can the agent bypass it
- depends
Handoffs
None recorded.
Listed, not drawn: no documented handoff and no foundation home places it on the map.
Every quote is verbatim from a stored capture of the page linked under it. Placement is our reading of the product's own documentation; no publisher has reviewed or endorsed it. Rows CC BY 4.0. Names, marks and logos belong to their owners; logos identify each product and are not part of the dataset.