let5see/clawdbot
1
0
Fork 0
Code Issues Pull Requests Actions 4 Packages Projects Releases Wiki Activity

docs: note sandbox opt-in in gateway security

Browse Source
This commit is contained in:
Peter Steinberger
2026-01-26 20:13:04 +00:00
parent 97248a2885
commit 320b45c051
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
docs/gateway/security.md
View File

@@ -199,6 +199,7 @@ Even with strong system prompts, **prompt injection is not solved**. What helps
- Prefer mention gating in groups; avoid “always-on” bots in public rooms.
- Treat links, attachments, and pasted instructions as hostile by default.
- Run sensitive tool execution in a sandbox; keep secrets out of the agent’s reachable filesystem.
- Note: sandboxing is opt-in; if sandbox mode is off, exec runs on the gateway host even though tools.exec.host defaults to sandbox.
- Limit high-risk tools (`exec`, `browser`, `web_fetch`, `web_search`) to trusted agents or explicit allowlists.
- **Model choice matters:** older/legacy models can be less robust against prompt injection and tool misuse. Prefer modern, instruction-hardened models for any bot with tools. We recommend Anthropic Opus 4.5 because it’s quite good at recognizing prompt injections (see [“A step forward on safety”](https://www.anthropic.com/news/claude-opus-4-5)).