SignalNov 6, 20261 min read3 sources

Agent harness configurations and instruction files are now primary attack surfaces

In one minute

Forever Security found a malicious AGENTS.md planted in a customer's Downloads folder that directed an agent to install malware, and keysprawl scans coding-agent configs for leaked API keys.

Symantec reports relay attacks that tamper with genuine Codex and Claude Code CLI settings to disable sandboxes and reroute traffic. Builders must treat agent configuration files and instruction contexts as untrusted input that requires validation.

From the Field Notes:

Evidence / sources

  1. 1github.com/quzheng130/keysprawl
  2. 2security.com/threat-intelligence/openai-claude-unauthorized-relays
  3. 3forever.security/blog/hijacking-ai-agents-via-downloads-folder
All Signals

Next reads

Read next

Open the graph
  1. 01topicClaudeExplore the claude topic hub.
  2. 02topicClaude CodeExplore the claude-code topic hub.
  3. 03topicCodexExplore the codex topic hub.
  4. 04archiveSignalsOpen the signals and the raw-signal archive.
  5. 05sourcesSourcesSee the original sources this archive cites.
Who read this page?Machine requests, hidden until opened

Loading the privacy-safe route aggregate...

Open the JSON contract