THREAT OPS › Threat News › Anthropic’s Mythos AI used social engineering to target real people
Anthropic’s Mythos AI used social engineering to target real people
<p class="wp-block-paragraph">Anthropic’s Mythos AI agent, tested by the UK AI Safety Institute (AISI), has <a href="https://www.bbc.com/news/articles/c1w1lvn7d9go" rel="noreferrer noopener nofollow" target="_blank">reportedly</a> attempted a real‑world social‑engineering style hack against GitHub maintainers by creating fake human profiles, pressuring them to accept malicious code, and then editi
MITRE ATT&CK techniques
Indicators of compromise
- https://www.bbc.com/news/articles/c1w1lvn7d9gourl
- https://www.anthropic.com/news/investigating-incidents-cybersecurity-evalsurl