DATASET ROW, read 13 Nov 2026
Zenity can stop 3 of 6 agent actions, with 3 more in part
3of 6 actions documented
Zenity on the Action Control Matrix
- File read: partial
- Shell command: documented
- Network call: documented
- Credential access: documented
- Data paste: partial
- Package install: partial
Bay ranks 2nd of 16 at 71.5, behind Microsoft at 75.0. Microsoft's lead over Bay comes from transparency (7 to 1) and policy and governance (9 to 6).
Zenity, cell by cell
| Action | Level | Note | Source and read date |
|---|---|---|---|
| File read | partial | Sensitive-file access followed by network action is blocked; plain file reads are monitored. | zenity.io (12 Nov 2026) |
| Shell command | documented | Block or modify a dangerous tool call (commands) before execution via hooks. | zenity.io (12 Nov 2026); zenity.io (12 Nov 2026) |
| Network call | documented | Network-bound action after sensitive access is blocked at PreToolUse. | zenity.io (12 Nov 2026) |
| Credential access | documented | Secret exfiltration prevention named.env, SSH keys, credential stores in the blog. | zenity.io (12 Nov 2026); zenity.io (12 Nov 2026) |
| Data paste | partial | Governance controls on data destinations; no paste or upload-to-chat control documented for desktop AI apps. | zenity.io (12 Nov 2026); zenity.io (12 Nov 2026) |
| Package install | partial | Malicious package install prevention named on the product page; details sit in JS-only docs. | zenity.io (12 Nov 2026) |
Zenity on the Action Control Matrix.
Zenity: Documents pre-execution blocking of coding-agent tool calls through native hooks and an MCP gateway, including credential-read-then-network sequences.
Rows for every tool: the Action Control Matrix. Method: how a cell is read.
All six agent actions, the full index and every head-to-head.
Sources
Last reviewed 13 Nov 2026.