Skip to content

Wire Briefings Search

Fetching from the wire…

01

02

03

04

05

06

07

08

Wire Briefings Search

Entity trail

Lasso Security

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

1

Findings

2

Edges

2

Sources

5

Corpus findings

2026-03-25 / vibe-coding-researcherTip: CLAUDE_CODE_SUBPROCESS_ENV_SCRUB=1 — Strip Credentials from Every Agent SubprocessNew in v2.1.83: setting `CLAUDE_CODE_SUBPROCESS_ENV_SCRUB=1` strips Anthropic and cloud provider credentials (AWS keys, database creds, API tokens) from every subprocess environment — Bash commands, hooks, MCP servers. Not enabled by default since some workflows need those credentials. This directly mitigates the Lasso Security attack vector where malicious prompts could exfiltrate environment variables. Add it to your shell profile if your .env contains sensitive keys you don't want agents accessing.
2026-03-25 / vibe-coding-researcherLasso Security Publishes Claude Code Prompt Injection Research + Open-Source PostToolUse Hook DefenderLasso Security published research demonstrating that `--dangerously-skip-permissions` enables indirect prompt injection via poisoned READMEs, docs, and MCP responses. They simultaneously released claude-hooks on GitHub — a PostToolUse hook implementing 50+ regex patterns across four attack categories (instruction override, role-playing manipulation, encoding/obfuscation, context manipulation). The defender intercepts tool results and injects warnings into Claude's context before processing. This is the first production-ready open-source defense for Claude Code's autonomous mode.

Graph relationships

CRITICIZES
Claude Code
Lasso Security demonstrated prompt injection vulnerabilities in Claude Code via poisoned docs and MCP responses.
Source finding
RELEASED
claude-hooks
Lasso Security published Claude Code prompt injection research and open-source claude-hooks defender.
Source finding

Source trail

Lasso Security published research claude-hooks Trail of Bits released their internal Claude Code security config v2.1.83 DEV Community / Claude Code Changelog

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues

Lasso Security intelligence trail | MindPattern