threatdeck
Live 13:45 UTC ·

OWASP Agentic

ASI05 · Unexpected Code Execution

Agents generate or run code that escapes the intended sandbox, leading to remote code execution.

OWASP Top 10 for Agentic Applications (2026)

Mitigations

  • Sandboxed execution with no ambient credentials
  • Egress restrictions
  • Review generated code before execution

Detections 3

Related techniques

In the news

  1. Attacks on AI Vulnerability MCP Server Watch: advisories High

    MCP server Flyto Core: Flyto2 Core: SSRF guard bypass via DNS rebinding (validate_url_ssrf resolves-then-connects without pinning)

    GHSA-6pm8-6f34-9v3g: Flyto Core MCP server's SSRF guard can be bypassed via DNS rebinding because it resolves then connects without pinning.

    PatchUpgrade flyto-core to 2.26.8 or later

    ASI02ASI05 #mcp#ssrf#dns-rebinding Brief In your stack
  2. Defensive AI Tooling OpenAI News

    Inside the Codex sandbox

    OpenAI describes how the Codex sandbox enforces user-controlled filesystem and network limits when running commands on macOS, Linux, and Windows.

    ASI05 #sandbox#codex#agents In your stack
  3. Defensive AI Tooling Simon Willison's Weblog Medium

    External sandboxes for coding agents

    Simon Willison and Prime Radiant released three external sandbox server implementations so agent-executed code runs outside the agent, limiting damage from prompt injection.

    LLM01ASI05 #sandbox#coding-agents#prompt-injection 1 min read Brief In your stack

Tools

Detect or mitigate it

Mappings are AI-assisted and checked against the framework definitions; corrections welcome.

Following

Follow the vendors, products, AI tools, techniques and actors you care about. Matching stories, CVEs and exploited bugs are marked, a Following tab appears in the feed, and returning visits show what changed. Saved only in this browser.

Presets

Get updates

A personal RSS feed of new stories on everything you follow. Paste it into any feed reader, Slack or Teams RSS app.