Tag: security

All the articles with the tag "security".

• OpenCode Denies `git`. It Runs `$(which git)` Just Fine.

  20 Jul, 2026

  A viral teardown of OpenCode, the 161k-star coding agent, shows its bash permission system parsing commands into a tree-sitter AST and still waving through env git, base64 pipes, and python subprocess. Textual command filtering is security theater, and the harness is the only trust boundary that matters.

• Weekly Roundup: One Adverb, One Agent, and Twelve Hosted Runtimes

  10 Jul, 2026

  GitHub's injection scanner fell to the word 'Additionally', a single-agent red-teaming harness beat the swarm it shipped with, and the managed-agent market got mapped.

• Abnormal AI Is Transforming in Public. So Is Its Attack Surface.

  9 Jul, 2026

  Abnormal AI turned its internal AI-adoption experiments into a public content stream. It's a clever recruiting play, and a reconnaissance gift to the exact attackers Abnormal sells protection against.

• The Managed-Agent Landscape: Twelve Ways to Not Run Your Own Agent

  8 Jul, 2026

  By mid-2026 the managed-agent market has settled into three layers of hosted runtimes, all selling the same promise. Here's the map, what you're actually buying, and the isolation label that BeyondTrust showed you shouldn't trust.