---
id: owasp-asi07-insecure-inter-agent-communication
track: coding
version: 0.0.2
label: advisory
keyword: advise
where: text
sha256: ca7d9044b1673a261c99b7146f11d7cfce4083e401d1fd388a4f073d5c0220ec
source: https://github.com/open-coder-ai/chock-catalog/tree/1e60d211c1bb767152c6ab0167932da06ab3a10f/agentic-security/owasp-asi07-insecure-inter-agent-communication
catalog_ref: 1e60d211c1bb767152c6ab0167932da06ab3a10f
---

# OWASP ASI07 — Insecure Inter-Agent Communication

owasp-asi07-insecure-inter-agent-communication · version 0.0.2

Advisory — Advisory only. It is skill text, and nothing stops a violation. Chock adds friction. It is not a security boundary. 

In a git repo: advisory (The agent reads the text, and nothing stops a violation.)



## What it does

Authenticate and integrity-protect the channels agents use to talk to each other, so a peer cannot be impersonated, a message tampered with, or a fake agent registered in discovery. Use when building multi-agent orchestration, agent-to-agent protocols, delegation between agents, message buses, or agent discovery services. Do NOT use for a single agent calling ordinary tools — that is \`owasp-asi02-tool-misuse\`.

## Its label on each agent

- Claude Code (tested): Advisory — Advisory only. It is skill text, and nothing stops a violation. Builder: /coding/builder/#client=claude-code&p=owasp-asi07-insecure-inter-agent-communication
- Cursor (tested): Advisory — Advisory only. It is skill text, and nothing stops a violation. Builder: /coding/builder/#client=cursor&p=owasp-asi07-insecure-inter-agent-communication
- Codex (tested): Advisory — Advisory only. It is skill text, and nothing stops a violation. Builder: /coding/builder/#client=codex&p=owasp-asi07-insecure-inter-agent-communication
- GitHub Copilot (tested): Advisory — Advisory only. It is skill text, and nothing stops a violation. Builder: /coding/builder/#client=copilot&p=owasp-asi07-insecure-inter-agent-communication
- Devin (tested): Advisory — Advisory only. It is skill text, and nothing stops a violation. Builder: /coding/builder/#client=devin&p=owasp-asi07-insecure-inter-agent-communication
- Grok (tested): Not graded yet for Grok. Builder: /coding/builder/#client=grok&p=owasp-asi07-insecure-inter-agent-communication
- goose (tested): Not graded yet for goose. Builder: /coding/builder/#client=goose&p=owasp-asi07-insecure-inter-agent-communication
- Antigravity (tested): Not graded yet for Antigravity. Builder: /coding/builder/#client=antigravity&p=owasp-asi07-insecure-inter-agent-communication
- OpenHands (untested): Not graded yet for OpenHands. Builder: /coding/builder/#client=openhands&p=owasp-asi07-insecure-inter-agent-communication
- Kimi Code (untested): Not graded yet for Kimi Code. Builder: /coding/builder/#client=kimi-code&p=owasp-asi07-insecure-inter-agent-communication
- Factory Droid (untested): Not graded yet for Factory Droid. Builder: /coding/builder/#client=factory-droid&p=owasp-asi07-insecure-inter-agent-communication

## What it misses

This policy does not state what it misses.

## Latest change

0.0.2 · 2026-09-29 — Point at the mechanised slice: the agentic-code-security gate's comms pack refuses TLS certificate verification switched off in Python and Node, at commit and at tool use. Everything else here stays advisory, and no rule text or claim is raised; the pointer is a see() and a references section.

## Provenance

- Tested by 0 of 6 cases run automatically
- SHA-256: `ca7d9044b1673a261c99b7146f11d7cfce4083e401d1fd388a4f073d5c0220ec`
- Catalog commit: https://github.com/open-coder-ai/chock-catalog/commit/1e60d211c1bb767152c6ab0167932da06ab3a10f
- Source: https://github.com/open-coder-ai/chock-catalog/tree/1e60d211c1bb767152c6ab0167932da06ab3a10f/agentic-security/owasp-asi07-insecure-inter-agent-communication (catalog path `agentic-security/owasp-asi07-insecure-inter-agent-communication`)
- Presets: OWASP agentic top 10
- JSON: `/api/coding/policies/owasp-asi07-insecure-inter-agent-communication.json`
- Report a problem: https://chock.sh/report/?policy=owasp-asi07-insecure-inter-agent-communication&version=0.0.2&page=%2Fcoding%2Fpolicies%2Fowasp-asi07-insecure-inter-agent-communication%2F