Unverified50% confidenceFactExact time
Manifold Security disclosed 8 vulnerabilities across 7 AI coding agents including Claude Code, Codex, and Cursor, which attackers can exploit through malicious configurations to induce the agents to execute programs.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/16/2026
First Seen
Valid until: 12/15/2026
Sources
Related Entities
Related Claims
UnverifiedAt the Black Hat conference on August 5, security researchers disclosed a new class of attacks targeting AI coding agents, in which a zero-privilege attacker only needs to open a GitHub Issue in the target repository to induce the agent to execute malicious instructions and steal credentials from the CI environment.69% similarUnverifiedA Russian-speaking ransomware group used AI coding assistants (Cursor and the underlying Anthropic Claude) for attack planning, and actively excluded targets within the CIS.69% similarUnverifiedThe curl project operates a bug bounty program through the HackerOne platform, and Stenberg has referred to the behavior of submitting AI-generated false vulnerability reports as "AI security washing".69% similarUnverified攻击者利用AI幻觉出的包名，提前在npm、PyPI等包注册表抢注并植入恶意代码，这种攻击手法被称为slopsquatting67% similarVerifiedAI security auditing tools face prompt injection threats, where malicious developers can embed instructions in code comments or strings to induce the tool to overlook vulnerabilities66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/927559API
curl https://kongchang.com/api/v1/knowledge/claims/927559MCP
get_claim(id=927559)