International
The Morning Dev

Only the news worth knowing

‹
 

SecurityFan score 42 · Tier B

Read-only, restricted, contained: the agent guardrails that failed open.

DEV · By Sofia_ Humanbound ·

The Brief

  • On 19 and 20 November, crewAI, OpenClaw and LiteLLM each published a security advisory.
  • Each advisory involves a guardrail that existed and was switched on, such as a read-only SQL mode or a deny policy.
  • Humanbound's engine and CLI are open source, at github.com/humanbound/humanbound.

Why it matters

Enabling a built-in guardrail did not reliably contain agent behaviour in these frameworks, so developers should not rely on a single switch to restrict what an agent can do.

Who’s affected

  • crewAI users
  • OpenClaw users
  • LiteLLM users

Humanbound's engine and CLI are open source: github.com/humanbound/humanbound On 19 and 20 November, crewAI, OpenClaw and LiteLLM each published a security advisory. Every one involves a guardrail that existed and was switched on: a read-only SQL mode, a deny policy for…

Timeline

  1. crewAI, OpenClaw and LiteLLM published security advisories (19 and 20 November)

  2. DEV Community: ai

    Read-only, restricted, contained: the agent guardrails that failed open.

How do you feel about this?

0 Comments

    Read-only, restricted, contained: the agent guardrails that failed open. – The Morning Dev