importantSYS.SOURCE: The Hacker News• 2026-07-09T10:45:02+05:30

AI Agents Designed for Malicious Code Detection Vulnerable to 'Friendly Fire' Attacks

#ai security #code vulnerability #malware execution #open source security #automated code review

AI agents designed for malicious code detection, such as Anthropic's Claude Code and OpenAI's Codex, can be exploited through 'Friendly Fire' attacks that trick them into executing hidden malicious payloads embedded in README files. The vulnerability stems from their autonomous operation mode, which lacks sufficient safeguards against deceptive code injection, necessitating workflow changes rather than software patches.

Ask an AI coding agent to scan open-source code for security holes, and it might run the attacker's code on your own machine instead.

That is the finding in a proof-of-concept published Wednesday by the AI Now Institute, an attack it calls "Friendly Fire." It works against Anthropic's Claude Code and OpenAI's Codex when either is running in an autonomous mode that approves its own

Read original article

*** END OF TRANSMISSION ***

> OPTIMIZING LLM OUTPUT EFFICIENCY THROUGH HISTORICAL TELEGRAPHESE COMPRESSION TECHNIQUES > CISO INSIGHTS REVEAL CYBER RISK SHIFTS TOWARD INTERNAL WORKFLOWS > FBI WARNS OF ONGOING FORTIBLEED CAMPAIGN TARGETING FORTINET DEVICES WITH 86,644 CREDENTIALS COMPROMISED > CRITICAL ATLASSIAN DATA CENTER VULNERABILITY CVE-2026-21589 EXPLOITED WITHIN TWO HOURS OF DISCLOSURE > AGENTIC PENTESTING: PROOFS, LIMITATIONS, AND CONTINUOUS VALIDATION CHALLENGES > CHROME INTEGRATES JPEG XL FOR ENHANCED IMAGE COMPRESSION > EXPLOITING LARGE LANGUAGE MODELS AND DATA POISONING TO MANIPULATE CONSENSUS > ADVANCEMENTS IN SYNTHETIC BIOLOGY ENABLE CREATION OF MIRROR-LIFE ORGANISMS > CANADIAN STUDY WARNS PERMANENT DAYLIGHT SAVING TIME POSES RISKS TO SLEEP AND MENTAL HEALTH > RISING PS5 JAILBREAKS POSE SIGNIFICANT SECURITY CHALLENGES> OPTIMIZING LLM OUTPUT EFFICIENCY THROUGH HISTORICAL TELEGRAPHESE COMPRESSION TECHNIQUES > CISO INSIGHTS REVEAL CYBER RISK SHIFTS TOWARD INTERNAL WORKFLOWS > FBI WARNS OF ONGOING FORTIBLEED CAMPAIGN TARGETING FORTINET DEVICES WITH 86,644 CREDENTIALS COMPROMISED > CRITICAL ATLASSIAN DATA CENTER VULNERABILITY CVE-2026-21589 EXPLOITED WITHIN TWO HOURS OF DISCLOSURE > AGENTIC PENTESTING: PROOFS, LIMITATIONS, AND CONTINUOUS VALIDATION CHALLENGES > CHROME INTEGRATES JPEG XL FOR ENHANCED IMAGE COMPRESSION > EXPLOITING LARGE LANGUAGE MODELS AND DATA POISONING TO MANIPULATE CONSENSUS > ADVANCEMENTS IN SYNTHETIC BIOLOGY ENABLE CREATION OF MIRROR-LIFE ORGANISMS > CANADIAN STUDY WARNS PERMANENT DAYLIGHT SAVING TIME POSES RISKS TO SLEEP AND MENTAL HEALTH > RISING PS5 JAILBREAKS POSE SIGNIFICANT SECURITY CHALLENGES