Start Debugging

prompt-injection

3 posts

2026-09-25 ai-agents claude-code mcp

How to Keep API Keys Out of a Coding Agent's Context With a Credential Gateway

Scoping a token does not stop a prompt-injected agent from leaking it. Moving the token out of the agent's process does. Three working setups: a 50-line gateway any agent can call, Claude Code 2.1.199+ sandbox masking with injectHosts, and Claude Managed Agents vaults, plus the measured leak that host-level injection still allows.

2026-09-03 ai-agents llm mcp

Information-Flow Control for AI Agents: Blocking Prompt Injection With Labels, Not Prompts

Defensive system prompts are heuristic. Information-flow control is not: label every piece of content with integrity and confidentiality, propagate most-restrictive-wins through every tool call, and check the label at the sink before it runs. An 80-line runnable harness, the Agent Framework FIDES implementation, and the false positives the pattern buys you.

2026-07-03 cursor ai-agents security

DuneSlide: Two Cursor Bugs That Turn Prompt Injection Into Zero-Click RCE

Cato AI Labs disclosed CVE-2026-50548 and CVE-2026-50549, a pair of 9.8 CVSS flaws in Cursor's terminal sandbox. A poisoned MCP response or web result can escape the sandbox and run code. Cursor 3.0 is the fix.