Unverified50% confidenceFactExact time
In its internal safety report, Anthropic lists AI-enabled bioweapon risk as a core subset of CBRN threats (chemical, biological, radiological, and nuclear threats).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/18/2026
First Seen
Valid until: 12/17/2026
Sources
Related Entities
Related Claims
VerifiedPrompt injection attacks were first publicly demonstrated by security researcher Riley Goodside in 2022 and have been listed by OWASP as the top security risk for LLM applications.65% similarUnverifiedBoth the National Security Agency (NSA) and the Cybersecurity and Infrastructure Security Agency (CISA) have published dedicated reports on AI threats.65% similarUnverified提示词注入攻击（Prompt Injection）是LLM应用当前最受关注的威胁向量之一，被斯坦福大学安全研究组列为首要安全风险64% similarVerifiedAI safety emphasizes defending against external threats and preventing system misuse, including prompt injection defense, jailbreak protection, data leakage prevention, and abuse detection.63% similarUnverifiedThe threat report covers five major categories of abuse scenarios: cyberattacks, influence operations, surveillance, the biological domain, and weapons manufacturing.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/931695API
curl https://kongchang.com/api/v1/knowledge/claims/931695MCP
get_claim(id=931695)