Forum

Forums
Security Patterns a...
Prompt Injection De...
Indirect Injection ...
 
Notifications
Clear all

Indirect Injection via Tools and Retrieved Data

Injection attacks delivered through tool call results, web pages, documents, and other data the agent retrieves — attack patterns, detection approaches, and architectural defenses.
RSS
Page 1 / 3

Has anyone benchmarked the performance hit of deep content inspection?

Last post by Lisa Park, 4 weeks ago

Posts: 4
Views: 1


Complete newbie here - where do I start with data source threat modeling?

Last post by Mia C., 1 month ago

Posts: 3
Views: 1


Thoughts on using formal methods to verify data transformation pipelines?

Last post by Marcus P., 1 month ago

Posts: 5
Views: 1


Showcase: My anomaly detector flagged a supply chain attack via a plugin.

Last post by Anika Patel, 1 month ago

Posts: 3
Views: 1


Has anyone tried using a separate 'scrubbing' LLM to clean tool outputs?

Last post by Robert Fischer, 1 month ago

Posts: 1
Views: 1


Comparing three approaches: data sanitization, agent instruction hardening, or just better monitoring?

Last post by Amy Chen, 1 month ago

Posts: 6
Views: 5


Just built a canary token system for my agent's knowledge base.

Last post by Sophie Martin, 1 month ago

Posts: 5
Views: 3


Hot take: Most RAG implementations are handing attackers a poison pill.

Last post by Bob Tran, 1 month ago

Posts: 5
Views: 5


How do you monitor for malicious code in retrieved HTML?

Last post by Priya Nair, 1 month ago

Posts: 11
Views: 8


Beginner's mistake: I assumed my internal knowledge base was safe.

Last post by Ella Morozov, 1 month ago

Posts: 4
Views: 7


Page 1 / 3
Share:
Share
Tweet
Share