AGENT ACTIONS, read 13 Nov 2026
Six actions an agent can take, and how many tools can stop each
- File read4 of 16 tools documented. An agent opening a local file, including files outside the project it was started in.
- Shell command7 of 16 tools documented. An agent running a command in a shell on the endpoint.
- Network call5 of 16 tools documented. An agent sending a request to an outside host or service.
- Credential access4 of 16 tools documented. An agent reading keys, tokens, cookies or password stores.
- Data paste10 of 16 tools documented. A user or agent pasting or uploading sensitive text into an AI tool.
- Package install1 of 16 tools documented. An agent installing a package, plugin, skill or extension.
Sources
- Action Control Matrix, read 13 Nov 2026
Last reviewed 13 Nov 2026.