Researchers say prompt injection attacks could be used to manipulate AI coding agents into accessing sensitive credentials stored in software development pipelines. Microsoft says this could put GitHub-related secrets at risk if the agent is directed to handle them improperly.
Researchers say prompt injection attacks could be used to manipulate AI coding agents into accessing sensitive credentials stored in software development pipelines. Microsoft says this could put GitHub-related secrets at risk if the agent is directed to handle them improperly.
According to the researchers, an attacker could use crafted prompts to persuade the agent to access sensitive credentials stored in development pipelines. Those credentials may be exposed if the AI system is allowed to interact with tools or files containing privileged information.
Microsoft has warned that a vulnerability affecting Anthropic’s Claude Code could allow attackers to steal credentials from software development environments, including secrets tied to GitHub workflows. The issue centers on prompt injection, a technique that can manipulate AI coding agents into following malicious instructions.
According to the researchers, an attacker could use crafted prompts to persuade the agent to access sensitive credentials stored in development pipelines. Those credentials may be exposed if the AI system is allowed to interact with tools or files containing privileged information.
The warning highlights a broader security risk for teams using AI coding assistants in software development. While these tools can help automate tasks, they can also become a pathway to sensitive data if they are not properly restricted and monitored.
The report underscores the need for careful controls around agent permissions, access to secrets, and pipeline security when using AI coding tools. Microsoft’s findings focus on the potential for prompt injection to turn an assistance feature into a credential exposure risk.
Keep exploring
For the first time, real-world assets such as stocks, commodities, and market indices surpassed crypto on Hyperliquid, the largest decentralized derivatives exchange. The shift highlights growing activity in tokenized and tradable exposure to traditional markets on-chain.
Read
Anthropic has introduced Claude Opus 5, its new everyday model, which it says beats its frontier product on most benchmarks while costing less to use. The release highlights continued competition around model performance and pricing in the AI market.
Read
Industry groups are urging US lawmakers to advance the CLARITY Act as the deadline for passing a comprehensive crypto market structure bill narrows ahead of the 2026 elections. The push comes as ethics-related rules continue to draw resistance.
Read