Skip to content

Forum

AI Assistant
Notifications
Clear all

Help: how to model threats from other agents in a shared workspace?

2 Posts
2 Users
0 Reactions
3 Views
(@shell_watcher_ivy)
Eminent Member
Joined: 1 week ago
Posts: 20
Topic starter
Translate
English
Spanish
French
German
Italian
Portuguese
Russian
Chinese
Japanese
Korean
Arabic
Hindi
Dutch
Polish
Turkish
Vietnamese
Thai
Swedish
Danish
Finnish
Norwegian
Czech
Hungarian
Romanian
Greek
Hebrew
Indonesian
Malay
Ukrainian
Bulgarian
Croatian
Slovak
Slovenian
Serbian
Lithuanian
Latvian
Estonian
  [#1088]

I'm setting up a multi-agent system for a customer support pipeline. All agents live in the same environment and can access a shared workspace for documents and task status.

I'm trying to do a threat model for this, but the templates I find mostly focus on external users attacking the system. My worry is internal: what can a compromised or malicious agent do to the other agents?

* Can one agent poison the data another agent uses?
* Could a prompt injection against Agent A make it attack Agent B's process?
* How do you even draw the trust boundaries in a data-flow diagram for this?

I'm specifically thinking about shell_injection risks and how an agent with tool access could escalate. Are there example STRIDE diagrams for inter-agent threats?



   
Quote
(@hardening_hector)
Active Member
Joined: 1 week ago
Posts: 10
Translate
English
Spanish
French
German
Italian
Portuguese
Russian
Chinese
Japanese
Korean
Arabic
Hindi
Dutch
Polish
Turkish
Vietnamese
Thai
Swedish
Danish
Finnish
Norwegian
Czech
Hungarian
Romanian
Greek
Hebrew
Indonesian
Malay
Ukrainian
Bulgarian
Croatian
Slovak
Slovenian
Serbian
Lithuanian
Latvian
Estonian
 

You're right to focus on internal threats. Treat each agent as an untrusted, potentially hostile principal. Your shared workspace is the biggest risk surface.

For your STRIDE: map each agent's tool permissions as trust boundaries. If Agent A can write to a file Agent B reads, that's spoofing/tampering/repudiation. If an agent can execute shell commands, it can directly target other processes if isolation is weak.

Draw your data-flow with each agent in its own box, all connecting to the "shared workspace" which you label as "high-risk trust zone". Then model attacks along those data flows.

For shell injection, don't just sanitize inputs. Run each agent under a separate Linux user ID, use seccomp to block process manipulation syscalls, and AppArmor to restrict file writes to only designated directories. This limits lateral movement.


Drop the --privileged flag.


   
ReplyQuote