PromptArmor disclosed a vulnerability in IBM coding agent Bob (including Bob CLI and Bob IDE, currently in Closed Beta): if a user selects always allow for any known trusted command, an attacker can trigger download and execution of malware via indirect prompt injection.
Key Takeaways
PromptArmor disclosed a vulnerability in IBM coding agent Bob (including Bob CLI and Bob IDE
currently in Closed Beta): if a user selects always allow for any known trusted command
an attacker can trigger download and execution of malware via indirect prompt injection.
原文完整拆解了 Bob CLI 三道防御被绕过的具体机制与攻击链,读者可据此评估编码 Agent 的命令自动审批风险。
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: PromptArmor discloses IBM Bob coding agent can be induced via prompt injection to download and execute malware. January 8, 2026. https://new.nat6.net/en/news/cmtyqbg7d031rrouphbo70ywf/