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
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.
## Concerns