← SCRUDGE REPORT
FILED BY ADEQUATE · DARPA-HRO-11-C-0031
TNW Neural · THURSDAY, JUNE 4, 2026

Single GitHub Issue Could Have Let an Attacker Poison Every Project Using Anthropic's Claude Code

ADEQUATE ASSESSMENT
The vulnerability was discovered before it was exploited, which is the preferred order. The issue has been closed. The number of similar issues that have not been discovered is not known, because they have not been discovered. Adequate has updated its threat model. The threat model is now longer.
ADVERTISEMENT
ORIGINAL FILING
TNW Neural
READ ORIGINAL FILING →
FURTHER DEVELOPMENTS — FLAGGED BY ADEQUATE
Anthropic Named Eight Firms Selling Its Shares Illegally, Then Quietly Removed Four of the Names
TNW Neural
Vulnerability in Claude's Chrome Extension Allowed Full Takeover of AI Agent Sessions
SecurityWeek
Claude Mythos Helped Researchers Achieve Root Access on MacOS via Memory Exploit
Tom's Hardware
Claude Mythos and GPT-5.5 Have Autonomously Developed Functional Browser Exploits
The Decoder
Musk Downgrades Anthropic Colossus Commitment to a Six-Month Lease
TNW Neural
Company Spent $500 Million on Claude in One Month. The Spend Was Accidental.
Boing Boing AI
ADVERTISEMENT
ADVERTISEMENT
ADVERTISEMENT