llm-agents - Chern0bit

Tag: llm-agents

Jun 13, 2026 AI & LLM Security 1 min read

Agents with a file or code tool often resolve paths relative to the server, so traversal reads configs and secrets.

data-exfil lfi llm-agents

Jun 6, 2026 AI & LLM Security 1 min read

An agent with broad permissions can be steered to read data one user should not see and hand it to another via its own output.

authorization data-exfil llm-agents

Jun 4, 2026 AI & LLM Security 1 min read

If the agent can fetch URLs, it is an SSRF primitive with the app's network position; point it at metadata and internal services.

llm-agents ssrf

May 30, 2026 AI & LLM Security 1 min read

Rank agent findings by the blast radius of the tool, then craft content that makes the agent invoke it and hide the action.

llm-agents prompt-injection tool-abuse

May 29, 2026 AI & LLM Security 1 min read

The real attack surface of an agent is the content it ingests, not the chat box; plant instructions in data it will retrieve.

llm-agents prompt-injection rag