brandon/oam
1
0
Fork 0
mirror of https://gitea.com/mcereda/oam.git synced 2026-02-09 05:44:23 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(kb/ai/agent): add missing note about reasoning being heplful against attacks

Browse Source
This commit is contained in:
Michele Cereda
2026-01-25 17:35:09 +01:00
parent 1d921eea44
commit bde75601ef
1 changed files with 3 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
knowledge base/ai/agent.md
View File

@@ -33,6 +33,9 @@ Prefer using **local** agents.
Consider limiting agent execution to containers or otherwise isolated environments, with only (limited) access to what Consider limiting agent execution to containers or otherwise isolated environments, with only (limited) access to what
they absolutely need. they absolutely need.
Enabling reasoning for the model _could™_ sometimes help avoiding attacks, since the model _might™_ be able to notice
them during the run.
Prefer **requiring** consent by agents when running them. Prefer **requiring** consent by agents when running them.
## Concerns ## Concerns